Search

Automated detection of retinal structures, such as retinal vessels (RV), the foveal avascular zone (FAZ), and retinal vascular junctions (RVJ), are of great importance for understanding diseases of the eye and clinical decision-making. In this paper, we propose a novel Voting-based Adaptive Feature Fusion multi-task network (VAFF-Net) for joint segmentation, detection, and classification of RV, FAZ, and RVJ in optical coherence tomography angiography (OCTA). A task-specific voting gate module is proposed to adaptively extract and fuse different features for specific tasks at two levels: features at different spatial positions from a single encoder, and features from multiple encoders. In particular, since the complexity of the microvasculature in OCTA images makes simultaneous precise localization and classification of retinal vascular junctions into bifurcation/crossing a challenging task, we specifically design a task head by combining the heatmap regression and grid classification. We take advantage of three different en face angiograms from various retinal layers, rather than following existing methods that use only a single en face. We carry out extensive experiments on three OCTA datasets acquired using different imaging devices, and the results demonstrate that the proposed method performs on the whole better than either the state-of-the-art single-purpose methods or existing multi-task learning solutions. We also demonstrate that our multi-task learning method generalizes across other imaging modalities, such as color fundus photography, and may potentially be used as a general multi-task learning tool. We also construct three datasets for multiple structure detection, and part of these datasets with the source code and evaluation benchmark have been released for public access. [ABSTRACT FROM AUTHOR]

Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on two 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being partially unable to reach the accuracies reported in the original papers, we compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. [ABSTRACT FROM AUTHOR]

Android malware is an ongoing threat to billions of smart devices’ security, ranging from mobile phones to car infotainment systems. Despite numerous approaches and previous studies to develop solutions for detecting and preventing Android malware, the rapid continuous development of new malware variants requires a careful reconsideration and the development of effective methods to identify malware families given a meager number of malware instances. In this paper, we present DroidMalVet, a novel Android malware family classification and detection approach that does not require to perform complex program analyses or utilize large feature sets. DroidMalVet is the first to use a promising, diverse, and small set of software metrics as features in a supervised learning platform to classify and detect various Android malware families. Our extensive empirical evaluations on two large public malware datasets show that DroidMalVet accurately detects both small and large malware families with F-Score accuracy of 94.4% and 96%, and AUC equal to 99.5% and 99.7% on the malware families in Drebin and AMD datasets, respectively. Moreover, our results demonstrate the superior performance of DroidMalVet in detecting small families (i.e., families with few samples). DroidMalVet complements existing approaches and presents an early warning tool for detecting known and emerging malware families. [ABSTRACT FROM AUTHOR]

Image classification needs to consider the existence of image degradations in practice. Although degraded images have various levels of degradation, the degradation levels are usually unknown. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The proposed network can automatically infer ensemble weights by using estimated degradation levels of degraded images and features of restored images, where the degradation levels are estimated internally. The proposed network is mainly discussed with JPEG distortion, while degradations of both Gaussian noise and blurring are also examined. We demonstrate that the proposed network can classify degraded images over various levels of degradation. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images. [ABSTRACT FROM AUTHOR]

In this paper, classification of mental task-root brain–computer interfaces (BCIs) is being investigated. The mental tasks are dominant area of investigations in BCI, which utmost interest as these system can be augmented life of people having severe disabilities. The performance of BCI model primarily depends on the construction of features from brain, electroencephalography (EEG), signal, and the size of feature vector, which are obtained through multiple channels. The availability of training samples to features are minimal for mental task classification. The feature selection is used to increase the ratio for the mental task classification by getting rid of irrelevant and superfluous features. This paper suggests an approach to augment the performance of a learning algorithm for the mental task classification on the utility of power spectral density (PSD) using feature selection. This paper also deals a comparative analysis of multivariate and univariate feature selection for mental task classification. After applying the above stated method, the findings demonstrate substantial improvements in the performance of learning model for mental task classification. Moreover, the efficacy of the proposed approach is endorsed by carrying out a robust ranking algorithm and Friedman’s statistical test for finding the best combinations and compare various combinations of PSD and feature selection methods. [ABSTRACT FROM AUTHOR]

Histopathological tissue classification is a simpler way to achieve semantic segmentation for the whole slide images, which can alleviate the requirement of pixel-level dense annotations. Existing works mostly leverage the popular CNN classification backbones in computer vision to achieve histopathological tissue classification. In this paper, we propose a super lightweight plug-and-play module, named Pyramidal Deep-Broad Learning (PDBL), for any well-trained classification backbone to improve the classification performance without a re-training burden. For each patch, we construct a multi-resolution image pyramid to obtain the pyramidal contextual information. For each level in the pyramid, we extract the multi-scale deep-broad features by our proposed Deep-Broad block (DB-block). We equip PDBL in three popular classification backbones, ShuffLeNetV2, EfficientNetb0, and ResNet50 to evaluate the effectiveness and efficiency of our proposed module on two datasets (Kather Multiclass Dataset and the LC25000 Dataset). Experimental results demonstrate the proposed PDBL can steadily improve the tissue-level classification performance for any CNN backbones, especially for the lightweight models when given a small among of training samples (less than 10%). It greatly saves the computational resources and annotation efforts. The source code is available at: https://github.com/linjiatai/PDBL. [ABSTRACT FROM AUTHOR]

The power distribution system’s fault root cause classification is an important but challenging problem. Traditional classifiers fail to achieve high accuracy and good generalization performance due to data insufficiency. A large volume of unlabeled data is available, which can be utilized to improve classification performance. This paper proposes a novel classifier called Robust Semi-Supervised Prototypical Network (RSSPN) based on Prototypical Network architecture and semi-supervised learning to address this issue. The proposed method can mine information from unlabeled data to improve the generalization ability and classification accuracy. Furthermore, RSSPN adopts the idea of meta-learning to obtain the “few-shot learning” ability for identifying new fault classes using very few samples encountered during the operation and update online. Experiments have been conducted on a dataset consisting of 1152 labeled samples belonging to 12 different classes and 10000 unlabeled samples. The accuracy of the proposed method is significantly better than the traditional classifiers. [ABSTRACT FROM AUTHOR]

Multi-label classification has gained in importance in the last decade and it is today confronted to the current needs to process massive raw data from heterogeneous sources. Therefore, dimensionality reduction, which aims at reducing the number of features, labels, or both, knows a renewed interest to enhance the scaling properties of the classifiers and their predictive performances. In this paper we review more than fifty papers presenting dimensionality reduction approaches for multi-label classification and we propose an analysis in three steps : (i) a typology of the methods describing the main components of their strategies, the problem they tackle and the way they solve it (ii) a unified formalization of the problems to help to distinguish the similarities and differences between the approaches, and (iii) a meta-analysis of the published experimental results inspired by the consensus theory to identify the most efficient algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel Semi-supervised Learning with Incomplete Modality (SLIM) method considering the modal consistency and complementarity simultaneously, and Kernel SLIM (SLIM-K) based on matrix completion for further solving the modal incompleteness. As is well known, most realistic data have multi-modal representations, multi-modal learning refers to the process of learning a precise model for complete modalities. However, due to the failures of data collection, self-deficiencies, or other various reasons, multi-modal examples are usually with incomplete modalities, which generate utility obstacle using previous methods. In this paper, SLIM integrates the intrinsic consistency and extrinsic complementary information for prediction and cluster simultaneously. In detail, SLIM forms different modal classifiers and clustering learner consistently in a unified framework, while using the extrinsic complementary information from unlabeled data against the insufficiencies brought by the incomplete modal issue. Moreover, in order to deal with missing modality in essence, we propose the SLIM-K, which takes the complemented kernel matrix into the classifiers and the cluster learner respectively. Thus, SLIM-K can solve the defects of missing modality in result. Finally, we give the discussion of generalization of incomplete modalities. Experiments on 13 benchmark multi-modal datasets and two real-world incomplete multi-modal datasets validate the effectiveness of our methods. [ABSTRACT FROM AUTHOR]

Metric-based methods achieve promising performance on few-shot classification by learning clusters on support samples and generating shared decision boundaries for query samples. However, existing methods ignore the inaccurate class center approximation introduced by the limited number of support samples, which consequently leads to biased inference. Therefore, in this paper, we propose to reduce the approximation error by class center calibration. Specifically, we introduce the so-called Pair-wise Similarity Module (PSM) to generate calibrated class centers adapted to the query sample by capturing the semantic correlations between the support and the query samples, as well as enhancing the discriminative regions on support representation. It is worth noting that the proposed PSM is a simple plug-and-play module and can be inserted into most metric-based few-shot learning models. Through extensive experiments in metric-based models, we demonstrate that the module significantly improves the performance of conventional few-shot classification methods on four few-shot image classification benchmark datasets. Codes are available at: https://github.com/PRIS-CV/Pair-wise-Similarity-module. [ABSTRACT FROM AUTHOR]

The difficulties of obtaining sufficient labeled samples have always been one of the factors hindering deep learning models from obtaining high accuracy in hyperspectral image (HSI) classification. To reduce the dependence of deep learning models on training samples, meta learning methods have been introduced, effectively improving the classification accuracy in small sample set scenarios. However, the existing methods based on meta learning still need to construct a labeled source data set with several pre-collected HSIs, and must utilize a large number of labeled samples for meta-training, which is actually time-consuming and labor-intensive. To solve this problem, this paper proposes a novel unsupervised meta learning method with multiview constraints for HSI small sample set classification. Specifically, the proposed method first builds an unlabeled source data set using unlabeled HSIs. Then, multiple spatial-spectral multiview features of each unlabeled sample are generated to construct tasks for unsupervised meta learning. Finally, the designed residual relation network is used for meta-training and small sample set classification based on the voting strategy. Compared with existing supervised meta learning methods for HSI classification, our method can only utilize HSIs without any label for unsupervised meta learning, which significantly reduces the number of requisite labeled samples in the whole classification process. To verify the effectiveness of the proposed method, extensive experiments are carried out on 8 public HSIs in the cross-domain and in-domain classification scenarios. The statistical results demonstrate that, compared with existing supervised meta learning methods and other advanced classification models, the proposed method can achieve competitive or better classification performance in small sample set scenarios. [ABSTRACT FROM AUTHOR]

Latent subspace learning aims to produce a latent representation for better reconstruction and classification from high-dimensional data through exploiting the optimal subspace. Current latent subspace learning methods commonly have three problems: 1) The discriminative property is ignored when learning the latent subspace, 2) The redundancy exists between the latent subspace and the prediction space, 3) There is no unified latent subspace that exploits knowledge jointly from the raw space, latent subspace, and label space. In this paper, we formulate the Joint Discriminative Latent Subspace Learning (JDLSL) problem to address these issues, and provide its optimization solution. JDLSL learns image representation from two aspects: a) the joint learning of latent subspaces for data reconstruction and prediction, b) the joint learning of label space and latent subspace for data reconstruction. To integrate knowledge from the joint learning, we organize the sparsity-induced latent subspace, where row-sparsity and column sparsity are simultaneously imposed. We provide the theoretical proof for the discriminativity learning ability of the sparsity-induced latent subspace. Extensive experiments and comparisons with the state-of-the-art showed that the proposed method has better performance. JDLSL shows a competitive performance with deep features compared to deep learning architectures, reflecting it potential integrating with deep learning. [ABSTRACT FROM AUTHOR]

Quasi-periodic time series (QTS) exists widely in the real world, and it is important to detect the anomalies of QTS. In this paper, we propose an automatic QTS anomaly detection framework (AQADF) consisting of a two-level clustering-based QTS segmentation algorithm (TCQSA) and a hybrid attentional LSTM-CNN model (HALCM). TCQSA first automatically splits the QTS into quasi-periods which are then classified by HALCM into normal periods or anomalies. Notably, TCQSA integrates a hierarchical clustering and the k-means technique, making itself highly universal and noise-resistant. HALCM hybridizes LSTM and CNN to simultaneously extract the overall variation trends and local features of QTS for modeling its fluctuation pattern. Furthermore, we embed a trend attention gate (TAG) into the LSTM, a feature attention mechanism (FAM) and a location attention mechanism (LAM) into the CNN to finely tune the extracted variation trends and local features according to their true importance to achieve a better representation of the fluctuation pattern of the QTS. On four public datasets, HALCM exceeds four state-of-the-art baselines and obtains at least 97.3 percent accuracy, TCQSA outperforms two cutting-edge QTS segmentation algorithms and can be applied to different types of QTSs. Additionally, the effectiveness of the attention mechanisms is quantitatively and qualitatively demonstrated. [ABSTRACT FROM AUTHOR]

Unsupervised 3D model analysis has attracted tremendous attentions with the increasing growth of 3D model data and the extensive human annotations. Many effective methods have been designed to address the 3D model analysis with labeled information, while rare methods devote to unsupervised deep learning due to the difficulty of mining reliable information. In this paper, we propose a novel unsupervised deep learning method named joint local correlation and global contextual information (LCGC) for 3D model retrieval and classification, which mines the reliable triplet set and uses triplet loss to optimize the deep neural network. Our method proposes two schemes: 1) Local self-correlation information learning, which adopts the intra and inter information to construct the view-level triplet set. 2) Global neighbor contextual information learning, which employs the neighbor contextual information to explore the reliable relations among 3D models and construct the model-level triplet set. The above schemes encourage that the selected triple set can been used to improve the discrimination of learned features. Extensive evaluations on two large-scale datasets, ModelNet40 and ShapeNet55, have demonstrated the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we propose a modified strategy using sparse representation to identify the authorship of online handwritten documents. The note-worthy aspect of this paper lies in the introduction of a-priori information for each dictionary atom, that in a way indicates its degree of importance with respect to the dynamic characteristics of the writer. The methodology behind obtaining this information for the dictionary atoms is based on the computation of entropy values over histograms that are generated from the sparse coefficients during the training phase. The prelearned values are incorporated on the traditional schemes of “max” and “mean” pooling of sparse codes, thereby resulting in a modified writer descriptor. Experiments performed with the proposed sparse classification strategy on the handwritten samples of the IAM and IBM-UB1 online handwriting databases demonstrate promising results. [ABSTRACT FROM AUTHOR]

Recently, substantial research effort has focused on how to apply CNNs or RNNs to better capture temporal patterns in videos, so as to improve the accuracy of video classification. In this paper, we investigate the potential of a purely attention based local feature integration. Accounting for the characteristics of such features in video classification, we first propose Basic Attention Clusters (BAC), which concatenates the output of multiple attention units applied in parallel, and introduce a shifting operation to capture more diverse signals. Experiments show that BAC can achieve excellent results on multiple datasets. However, BAC treats all feature channels as an indivisible whole, which is suboptimal for achieving a finer-grained local feature integration over the channel dimension. Additionally, it treats the entire local feature sequence as an unordered set, thus ignoring the sequential relationships. To improve over BAC, we further propose the channel pyramid attention schema by splitting features into sub-features at multiple scales for coarse-to-fine sub-feature interaction modeling, and propose the temporal pyramid attention schema by dividing the feature sequences into ordered sub-sequences of multiple lengths to account for the sequential order. Our final model pyramid×pyramid attention clusters (PPAC) combines both channel pyramid attention and temporal pyramid attention to focus on the most important sub-features, while also preserving the temporal information of the video. We demonstrate the effectiveness of PPAC on seven real-world video classification datasets. Our model achieves competitive results across all of these, showing that our proposed framework can consistently outperform the existing local feature integration methods across a range of different scenarios. [ABSTRACT FROM AUTHOR]

The multi-label image classification problem is one of the most important problems in the field of computer vision, which needs to predict and output all the labels in an image. Multiple labels to be classified in an image increases the difficulty of image classification, and multi-label image classification usually requires additional attention to the positions of the object with different scales and poses. Hence, how to use the dependency relationship between labels to improve the recognition accuracy is an important problem when the object is difficult to directly identify. In this paper, we propose a designed network called the Semantic Supplementary Network with Prior Information (SSNP) to address this problem. The proposed SSNP first generates prior information by using a prior information network with different convolutional layers. Then the semantic supplementary module generates semantic information of the potential labels that is highly relevant to the current information based on the prior information, thereby effectively using the dependency relationship between the labels to improve the classification accuracy. Different from existing methods which pay more attention to the image feature extraction process, we focus on the impact of high-level semantic information generated after feature extraction on the results and tap the potential of high-level semantic information through a semantic supplementary module to strengthen the potential dependence between labels. Experimental results on public benchmark datasets demonstrate that the proposed architecture achieves the state-of-the-art performance, especially when predicting some semantically dependent labels. [ABSTRACT FROM AUTHOR]

As the extension of high efficiency video coding (HEVC) standard, three dimensional-HEVC (3D-HEVC) is the latest 3D video coding standard. 3D-HEVC adopts many complicated coding algorithms to generate additional intermediate views for 3D video representation, which result in extremely high coding complexity. Therefore, this paper proposed a fast depth intra coding approach to reduce the 3D-HEVC complexity, which is based on convolutional neural network (CNN). First, we established a database based on the independent view of the depth map, which includes coding unit (CU) partition data of the depth map. Second, we constructed a depth edge classification CNN (DEC-CNN) framework to classify the edges for the depth map and embedded the network into a 3D-HEVC test platform. Finally, we utilized the pixel value of the binarized depth image to correct the above classification results. The experimental results demonstrated that our approach can reduce the intra coding time by 72.5% on average under negligible degradation of coding performance. This result outperforms the other state-of-the-art methods to reduce the coding complexity of 3D-HEVC. [ABSTRACT FROM AUTHOR]

Power Normalizations (PN) are useful non-linear operators which tackle feature imbalances in classification problems. We study PNs in the deep learning setup via a novel PN layer pooling feature maps. Our layer combines the feature vectors and their respective spatial locations in the feature maps produced by the last convolutional layer of CNN into a positive definite matrix with second-order statistics to which PN operators are applied, forming so-called Second-order Pooling (SOP). As the main goal of this paper is to study Power Normalizations, we investigate the role and meaning of MaxExp and Gamma, two popular PN functions. To this end, we provide probabilistic interpretations of such element-wise operators and discover surrogates with well-behaved derivatives for end-to-end training. Furthermore, we look at the spectral applicability of MaxExp and Gamma by studying Spectral Power Normalizations (SPN). We show that SPN on the autocorrelation/covariance matrix and the Heat Diffusion Process (HDP) on a graph Laplacian matrix are closely related, thus sharing their properties. Such a finding leads us to the culmination of our work, a fast spectral MaxExp which is a variant of HDP for covariances/autocorrelation matrices. We evaluate our ideas on fine-grained recognition, scene recognition, and material classification, as well as in few-shot learning and graph classification. [ABSTRACT FROM AUTHOR]

In this paper, we develop a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based graph convolutional network (GCN) models, but also bridges the theoretical gap between traditional convolutional neural network (CNN) models and spatially-based GCN models. Furthermore, the proposed BASGCN model can both adaptively discriminate the importance between specified vertices during the convolution process and reduce the notorious tottering problem of existing spatially-based GCNs related to the Weisfeiler-Lehman algorithm, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Semiconductor manufacturing is on the cusp of a revolution – the Internet of Things (IoT). With IoT we can connect all the equipment and feed information back to the factory so that quality issues can be detected. In this situation, more and more edge devices are used in wafer inspection equipment. This edge device must have the ability to quickly detect defects. Therefore, how to develop a high-efficiency architecture for automatic defect classification to be suitable for edge devices is the primary task. In this paper, we present a novel architecture that can perform defect classification in a more efficient way. The first function is self-proliferation, using a series of linear transformations to generate more feature maps at a cheaper cost. The second function is self-attention, capturing the long-range dependencies of feature map by the channel-wise and spatial-wise attention mechanism. We named this method as self-proliferation-and-attention neural network (SP&A-Net). This method has been successfully applied to various defect pattern classification tasks. Compared with other latest methods, SP&A-Net has higher accuracy and lower computation cost in many defect inspection tasks. [ABSTRACT FROM AUTHOR]

Fault diagnosis of bearings using classification techniques plays an important role in industrial applications, and, hence, has received increasing attention. Recently, significant efforts have been made to develop various methods for bearing fault classification and the application of Case Western Reserve University (CWRU) data for validation has become a standard reference to test the fault classification algorithms. However, a systematic research for evaluating bearing fault classification performance using the CWRU data is still lacking. This paper aims to provide a comprehensive benchmark analysis of the CWRU data using various entropy and classification methods. The main contribution of this paper is applying entropy-based fault classification methods to establish a benchmark analysis of entire CWRU datasets, aiming to provide a proper assessment of any new classification methods. Recommendations are provided for the selection of the CWRU data to aid in testing new fault classification algorithms, which will enable the researches to develop and evaluate various diagnostic algorithms. In the end, the comparison results and discussion are reported as a useful baseline for future research. [ABSTRACT FROM AUTHOR]

Artificial intelligence evolved as a powerful tool in condition monitoring of the induction motor for early diagnosis of bearing faults. This paper attempted to identify the features to improve the accuracy of diagnosis using the benchmark database of the Case Western Reserve University (CWRU) and the Machinery Fault Prevention Technology (MFPT). In this paper, 18 time-domain features are extracted constituting six proposed time-dependent spectral features (TDSFs) and 12 statistical time-domain features. For the first time, a set of six TDSFs are extracted to diagnose the bearing faults. This involves extracting frequency-domain features using the relationship between Parseval’s theorem and the Fourier transform directly from the time domain. Particle swarm optimization (PSO) and wheel-based differential evolution (WBDE) feature selection algorithms are also implemented to identify four prominent features. It is found that three of the four selected features are TDSF features, and results of selected features revealed the attainment of 90.92% for 48 class identifications of CWRU database and 100% for 17 class identifications of the MFPT database, respectively. [ABSTRACT FROM AUTHOR]

Objective: Preterm birth is the first cause of perinatal morbidity and mortality. Despite continuous clinical routine improvements, the preterm rate remains steady. Moreover, the specificity of the early diagnosis stays poor as many hospitalized women for preterm delivery threat finally deliver at term. In this context, the use of electrohysterograms may increase the sensitivity and the specificity of early diagnosis of preterm labor. Methods: This paper proposes a clinical application of electrohysterogram processing for the classification of patients as prone to deliver within a week or later. The approach relies on non-linear correlation analysis for the contraction bursts extraction and uses computation of various features combined with the use of Gaussian mixture models for their classification. The method is tested on a new dataset of 68 records collected on women hospitalized for preterm delivery threat. Results: This paper presents promising results for the automatic segmentation of the contraction and a classification sensitivity, specificity, and accuracy of, respectively, 80.7%, 76.3%, and 76.2%. Conclusion: These results are in accordance with the gold standards but have the advantage to be non-invasive and could be performed at home. Significance: Diagnosis of imminent labor is possible by electrohysterography recording and may help in avoiding over-medication and in providing better cares to at-risk pregnant women. [ABSTRACT FROM AUTHOR]

In this paper, we propose to leverage freely available unlabeled video data to facilitate few-shot video classification. In this semi-supervised few-shot video classification task, millions of unlabeled data are available for each episode during training. These videos can be extremely imbalanced, while they have profound visual and motion dynamics. To tackle the semi-supervised few-shot video classification problem, we make the following contributions. First, we propose a label independent memory (LIM) to cache label related features, which enables a similarity search over a large set of videos. LIM produces a class prototype for few-shot training. This prototype is an aggregated embedding for each class, which is more robust to noisy video features. Second, we integrate a multi-modality compound memory network to capture both RGB and flow information. We propose to store the RGB and flow representation in two separate memory networks, but they are jointly optimized via a unified loss. In this way, mutual communications between the two modalities are leveraged to achieve better classification performance. Third, we conduct extensive experiments on the few-shot Kinetics-100, Something-Something-100 datasets, which validates the effectiveness of leveraging the accessible unlabeled data for few-shot classification. [ABSTRACT FROM AUTHOR]

In many real-world scenarios, data from multiple modalities (sources) are collected during a development phase. Such data are referred to as multiview data. While additional information from multiple views often improves the performance, collecting data from such additional views during the testing phase may not be desired due to the high costs associated with measuring such views or, unavailability of such additional views. Therefore, in many applications, despite having a multiview training data set, it is desired to do performance testing using data from only one view. In this paper, we present a multiview feature selection method that leverages the knowledge of all views and use it to guide the feature selection process in an individual view. We realize this via a multiview feature weighting scheme such that the local margins of samples in each view are maximized and similarities of samples to some reference points in different views are preserved. Also, the proposed formulation can be used for cross-view matching when the view-specific feature weights are pre-computed on an auxiliary data set. Promising results have been achieved on nine real-world data sets as well as three biometric recognition applications. On average, the proposed feature selection method has improved the classification error rate by 31 percent of the error rate of the state-of-the-art. [ABSTRACT FROM AUTHOR]

This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method does not require additional annotations of object parts or textures for supervision. Instead, we use the same training data as traditional CNNs. Our method automatically assigns each interpretable filter in a high conv-layer with an object part of a certain category during the learning process. Such explicit knowledge representations in conv-layers of the CNN help people clarify the logic encoded in the CNN, i.e., answering what patterns the CNN extracts from an input image and uses for prediction. We have tested our method using different benchmark CNNs with various architectures to demonstrate the broad applicability of our method. Experiments have shown that our interpretable filters are much more semantically meaningful than traditional filters. [ABSTRACT FROM AUTHOR]

Due to the wide applications in a rapidly increasing number of different fields, 3D shape recognition has become a hot topic in the computer vision field. Many approaches have been proposed in recent years. However, there remain huge challenges in two aspects: exploring the effective representation of 3D shapes and reducing the redundant complexity of 3D shapes. In this paper, we propose a novel deep-attention network (DAN) for 3D shape representation based on multiview information. More specifically, we introduce the attention mechanism to construct a deep multiattention network that has advantages in two aspects: 1) information selection, in which DAN utilizes the self-attention mechanism to update the feature vector of each view, effectively reducing the redundant information, and 2) information fusion, in which DAN applies attention mechanism that can save more effective information by considering the correlations among views. Meanwhile, deep network structure can fully consider the correlations to continuously fuse effective information. To validate the effectiveness of our proposed method, we conduct experiments on the public 3D shape datasets: ModelNet40, ModelNet10, and ShapeNetCore55. Experimental results and comparison with state-of-the-art methods demonstrate the superiority of our proposed method. Code is released on https://github.com/RiDang/DANN. [ABSTRACT FROM AUTHOR]

In this paper we consider high-dimensional multiclass classification by sparse multinomial logistic regression. We propose first a feature selection procedure based on penalized maximum likelihood with a complexity penalty on the model size and derive the nonasymptotic bounds for misclassification excess risk of the resulting classifier. We establish also their tightness by deriving the corresponding minimax lower bounds. In particular, we show that there is a phase transition between small and large number of classes. The bounds can be reduced under the additional low noise condition. To find a penalized maximum likelihood solution with a complexity penalty requires, however, a combinatorial search over all possible models. To design a feature selection procedure computationally feasible for high-dimensional data, we propose multinomial logistic group Lasso and Slope classifiers and show that they also achieve the minimax order. [ABSTRACT FROM AUTHOR]

Arrhythmia detection and classification is a crucial step for diagnosing cardiovascular diseases. However, deep learning models that are commonly used and trained in end-to-end fashion are not able to provide good interpretability. In this paper, we address this deficiency by proposing the first novel interpretable arrhythmia classification approach based on a human-machine collaborative knowledge representation. Our approach first employs an AutoEncoder to encode electrocardiogram signals into two parts: hand-encoding knowledge and machine-encoding knowledge. A classifier then takes as input the encoded knowledge to classify arrhythmia heartbeats with or without human in the loop (HIL). Experiments and evaluation on the MIT-BIH Arrhythmia Database demonstrate that our new approach not only can effectively classify arrhythmia while offering interpretability, but also can improve the classification accuracy by adjusting the hand-encoding knowledge with our HIL mechanism. [ABSTRACT FROM AUTHOR]

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. Most existing deep models for multi-label text classification consider either the non-consecutive and long-distance semantics or the sequential semantics. However, how to coherently take them into account is still far from studied. In addition, most existing methods treat output labels as independent medoids, ignoring the hierarchical relationships among them, which leads to a substantial loss of useful semantic information. In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification. Specifically, we first propose to model each document as a word order preserved graph-of-words and normalize it as a corresponding word matrix representation preserving both the non-consecutive, long-distance and local sequential semantics. Then the word matrix is input to the proposed attentional graph capsule recurrent CNNs for effectively learning the semantic features. To leverage the hierarchical relations among the class labels, we propose a hierarchical taxonomy embedding method to learn their representations, and define a novel weighted margin loss by incorporating the label representation similarity. Extensive evaluations on three datasets show that our model significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Recently, automatic diagnostic approaches have been widely used to classify ocular diseases. Most of these approaches are based on a single imaging modality (e.g., fundus photography or optical coherence tomography (OCT)), which usually only reflect the oculopathy to a certain extent, and neglect the modality-specific information among different imaging modalities. This paper proposes a novel modality-specific attention network (MSAN) for multi-modal retinal image classification, which can effectively utilize the modality-specific diagnostic features from fundus and OCT images. The MSAN comprises two attention modules to extract the modality-specific features from fundus and OCT images, respectively. Specifically, for the fundus image, ophthalmologists need to observe local and global pathologies at multiple scales (e.g., from microaneurysms at the micrometer level, optic disc at millimeter level to blood vessels through the whole eye). Therefore, we propose a multi-scale attention module to extract both the local and global features from fundus images. Moreover, large background regions exist in the OCT image, which is meaningless for diagnosis. Thus, a region-guided attention module is proposed to encode the retinal layer-related features and ignore the background in OCT images. Finally, we fuse the modality-specific features to form a multi-modal feature and train the multi-modal retinal image classification network. The fusion of modality-specific features allows the model to combine the advantages of fundus and OCT modality for a more accurate diagnosis. Experimental results on a clinically acquired multi-modal retinal image (fundus and OCT) dataset demonstrate that our MSAN outperforms other well-known single-modal and multi-modal retinal image classification methods. [ABSTRACT FROM AUTHOR]

Collective classification has attracted considerable attention in the last decade, where the labels within a group of instances are correlated and should be inferred collectively, instead of independently. Conventional approaches on collective classification mainly focus on exploiting simple relational features (such as count and exists aggregators on neighboring nodes). However, many real-world applications involve complex dependencies among the instances, which are obscure/hidden in the networks. To capture these dependencies in collective classification, we need to go beyond simple relational features and extract deep dependencies between the instances. In this paper, we study the problem of deep collective classification in Heterogeneous Information Networks (HINs), which involve different types of autocorrelations, from simple to complex relations, among the instances. Different from conventional autocorrelations, which are given explicitly by the links in the network, complex autocorrelations are obscure/hidden in HINs, and should be inferred from existing links in a hierarchical order. This problem is highly challenging due to the multiple types of dependencies among the nodes and the complexity of the relational features. In this study, we proposed a deep convolutional collective classification method, called GraphInception, to learn the deep relational features in HINs. And we presented two versions of the models with different inference styles. The proposed methods can automatically generate a hierarchy of relational features with different complexities. Extensive experiments on four real-world networks demonstrate that our approach can improve the collective classification performance by considering deep relational features in HINs. [ABSTRACT FROM AUTHOR]

Recently, researchers have shown the powerful ability of deep methods with multilayers to extract high-level features and to obtain better performance for hyperspectral image classification. However, a common problem of traditional deep models is that the learned deep models might be suboptimal because of the limited number of training samples, especially for the image with large intraclass variance and low interclass variance. In this paper, novel convolutional neural networks (CNNs) with multiscale convolution (MS-CNNs) are proposed to address this problem by extracting deep multiscale features from the hyperspectral image. Moreover, deep metrics usually accompany with MS-CNNs to improve the representational ability for the hyperspectral image. However, the usual metric learning would make the metric parameters in the learned model tend to behave similarly. This similarity leads to obvious model’s redundancy and, thus, shows negative effects on the description ability of the deep metrics. Traditionally, determinantal point process (DPP) priors, which encourage the learned factors to repulse from one another, can be imposed over these factors to diversify them. Taking advantage of both the MS-CNNs and DPP-based diversity-promoting deep metrics, this paper develops a CNN with multiscale convolution and diversified metric to obtain discriminative features for hyperspectral image classification. Experiments are conducted over four real-world hyperspectral image data sets to show the effectiveness and applicability of the proposed method. Experimental results show that our method is better than original deep models and can produce comparable or even better classification performance in different hyperspectral image data sets with respect to spectral and spectral–spatial features. [ABSTRACT FROM AUTHOR]

This paper proposes a novel intelligent fault diagnosis method to automatically identify different health conditions of wind turbine (WT) gearbox. Unlike traditional approaches, where feature extraction and classification are separately designed and performed, this paper aims to automatically learn effective fault features directly from raw vibration signals while classify the type of faults in a single framework, thus providing an end-to-end learning-based fault diagnosis system for WT gearbox without additional signal processing and diagnostic expertise. Considering the multiscale characteristics inherent in vibration signals of a gearbox, a new multiscale convolutional neural network (MSCNN) architecture is proposed to perform multiscale feature extraction and classification simultaneously. The proposed MSCNN incorporates multiscale learning into the traditional CNN architecture, which has two merits: 1) high-level fault features can be effectively learned by the hierarchical learning structure with multiple pairs of convolutional and pooling layers; and 2) multiscale learning scheme can capture complementary and rich diagnosis information at different scales. This greatly improves the feature learning ability and enables better diagnosis performance. The proposed MSCNN approach is evaluated through experiments on a WT gearbox test rig. Experimental results and comprehensive comparison analysis with respect to the traditional CNN and traditional multiscale feature extractors have demonstrated the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

In active and assisted living environments, a major service that can be provided is the automated assessment of elderly people’s well-being. Therefore, activity recognition is required to detect what types of help disabled persons need to support them in their daily life activities. Unfortunately, it is still a difficult task to estimate the size of the required window for online sensor data streams to recognize a specific activity, especially when new sensor events are recorded. This paper proposes a windowing algorithm, which presents promising results to recognize complex human activities for multi-resident homes. The approach is based on the analysis of the sensor data to identify the best fitting sensors that should be considered in a specified window. Moreover, the second part of this paper proposes a set of different statistical spatio-temporal features to recognize human activities. In order to check the overall performance, this approach is tested using the CASAS data set and artificially generated laboratory data using our HBMS simulator. The results show high performance based on different evaluation metrics compared to other approaches. We believe that the proposed windowing approach provides a good approximation of the required window size in order to robustly detect human activities in comparison to other windowing approaches. [ABSTRACT FROM AUTHOR]

Classifying Internet traffic is critical to many network management tasks, including malicious attack detection, usage monitoring, load balancing, etc. As current traffic packets are often transmitted with encryption, at randomized port numbers, and under highly dynamic network conditions, traditional approaches such as port mapping, deep packet inspection, and statistical analysis are no longer effective. In this paper, we first collect extensive traffic flows at the exit router of a university and label them into various source applications. After extracting the message (consisting of multiple consecutive TCP packets) sequence for all collected traffic flows, we find that each application type has distinct sequential message features. By leveraging the message sequential feature, we develop a system, named SMC (Sequential Message Characterization), which can perform online traffic classification with the sequential size information of a few message segments. In SMC, after confirming the long-term dependency among message segments, we create a Long Short-Term Memory (LSTM) neural network to conduct deep learning on message size sequence, and then build a multi-classifier to classify traffic types based on the probability profiles output by deep LSTM models. Extensive experiments are conducted and results demonstrate that the proposed SMC can achieve 97% of classification accuracy on average. Meanwhile, with as few as 6 pieces of message size information as input, SMC enables early online traffic classification especially for heavy-traffic flows with over 35 message segments in median. [ABSTRACT FROM AUTHOR]

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep networks under small sample sizes, learning discriminative features is crucial. To this end, several loss functions have been proposed to encourage large intra-class compactness and inter-class separability. In this paper, we propose to enhance the discriminative power of features from a new perspective by introducing a novel neural network termed Relation-and-Margin learning Network (ReMarNet). Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Specifically, a relation network is used to learn the features that can support classification based on the similarity between a sample and a class prototype; at the meantime, a fully connected network with the cross entropy loss is used for classification via the decision boundary. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples and achieves competitive performance against state-of-the-art methods. Code is available at https://github.com/liyunyu08/ReMarNet. [ABSTRACT FROM AUTHOR]

Semi-supervised learning models for multiview data are important in image classification tasks, since heterogeneous features are easy to obtain and semi-supervised schemes are economical and effective. To model the view importance, conventional graph-based multiview learning models learn a linear combination of views while assuming a priori weights distribution. In this paper, we present a novel structural regularized semi-supervised model for multiview data, termed Adaptive MUltiview SEmi-supervised model (AMUSE). Our new model learns weights from a priori graph structure, which is more reasonable than weight regularization. Theoretical analysis reveals the significant difference between AMUSE and the prior arts. An efficient optimization algorithm is provided to solve the new model. Experimental results on six real-world data sets demonstrate the effectiveness of the structural regularized weights learning scheme. [ABSTRACT FROM AUTHOR]

The importance of effective surgical wound care cannot never be underestimated. Poorly managing surgical wounds may cause many serious complications. Thus, it raises the necessity to develop a patient-friendly self-care system which can help both patients and medical professionals to ensure the state of the surgical wounds without any special medical equipment. In this paper, a surgical wound assessment system for self-care is proposed. The proposed system is designed to enable patients capture surgical wound images of themselves by using a mobile device and upload these images for analysis. Combining image-processing and machine-learning techniques, the proposed method is composed of four phases. First, images are segmented into superpixels where each superpixel contains the pixels in the similar color distribution. Second, these superpixels corresponding to the skin are identified and the area of connected skin superpixels is derived. Third, surgical wounds will be extracted from this area based on the observation of the texture difference between skin and wounds. Lastly, state and symptoms of surgical wound will be assessed. Extensive experimental results are conducted. With the proposed method, more than 90% state assessment results are correct and more than 91% symptom assessment results consistent with the actual diagnosis. Moreover, case studies are provided to show the advantage and limitation of this system. These results show that this system could perform well in the practical self-care scenario. [ABSTRACT FROM AUTHOR]

The goal of early action recognition is to predict action label when the sequence is partially observed. The existing methods treat the early action recognition task as sequential classification problems on different observation ratios of an action sequence. Since these models are trained by differentiating positive category from all negative classes, the diverse information of different negative categories is ignored, which we believe can be collected to help improve the recognition performance. In this paper, we step towards to a new direction by introducing category exclusion to early action recognition. We model the exclusion as a mask operation on the classification probability output of a pre-trained early action recognition classifier. Specifically, we use policy-based reinforcement learning to train an agent. The agent generates a series of binary masks to exclude interfering negative categories during action execution and hence help improve the recognition accuracy. The proposed method is evaluated on three benchmark recognition datasets, NTU-RGBD, First-Person Hand Action, as well as UCF-101. The proposed method enhances the recognition accuracy consistently over all different observation ratios on the three datasets, where the accuracy improvements on the early stages are especially significant. [ABSTRACT FROM AUTHOR]

Classification is an important technique for remote sensing data interpretation. In order to enhance the performance of a supervised classifier and ensure the lowest possible cost of the training samples used in the process, active learning (AL) can be used to optimize the training sample set. At the same time, integrating spatial information can help to enhance the separability between similar classes, which can in turn reduce the need for training samples in AL. To effectively integrate spatial information into the AL framework, this paper proposes a new active relearning (ARL) model for remote sensing image classification. In particular, our model is used to relearn the spatial features on the classification map, which contributes significantly to enhancing the performance of the classifier. We integrate the relearning model into the AL framework, with the aim to accelerate the convergence of AL and further reduce the labeling cost. Under the newly developed ARL framework, we propose two spatial–spectral uncertainty criteria to optimize the procedure for selecting new training samples. Furthermore, an adaptive multiwindow ARL model is also introduced in this paper. Our experiments with two hyperspectral images and two very high resolution images indicate that the ARL model exhibits faster convergence speed with fewer samples than traditional AL methods. Our results also suggest that the proposed spatial–spectral uncertainty criteria and the multiwindow version can further improve the performance when implementing ARL. [ABSTRACT FROM AUTHOR]

Kernel methods, e.g., composite kernels (CKs) and spatial-spectral kernels (SSKs), have been demonstrated to be an effective way to exploit the spatial-spectral information nonlinearly for improving the classification performance of hyperspectral image (HSI). However, these methods are always conducted with square-shaped window or superpixel techniques. Both techniques are likely to misclassify the pixels that lie at the boundaries of class, and thus a small target is always smoothed away. To alleviate these problems, in this paper, we propose a novel patch-based low rank component induced spatial-spectral kernel method, termed LRCISSK, for HSI classification. First, the latent low-rank features of spectra in each cubic patch of HSI are reconstructed by a low rank matrix recovery (LRMR) technique, and then, to further explore more accurate spatial information, they are used to identify a homogeneous neighborhood for the target pixel (i.e., the centroid pixel) adaptively. Finally, the adaptively identified homogenous neighborhood which consists of the latent low-rank spectra is embedded into the spatial-spectral kernel framework. It can easily map the spectra into the nonlinearly complex manifolds and enable a classifier (e.g., support vector machine, SVM) to distinguish them effectively. Experimental results on three real HSI datasets validate that the proposed LRCISSK method can effectively explore the spatial-spectral information and deliver superior performance with at least 1.30% higher OA and 1.03% higher AA on average when compared to other state-of-the-art classifiers. [ABSTRACT FROM AUTHOR]

PCa is a disease with a wide range of tissue patterns and this adds to its classification difficulty. Moreover, the data source heterogeneity, i.e. inconsistent data collected using different machines, under different conditions, by different operators, from patients of different ethnic groups, etc., further hinders the effectiveness of training a generalized PCa classifier. In this paper, for the first time, a Generative Adversarial Network (GAN)-based three-player minimax game framework is used to tackle data source heterogeneity and to improve PCa classification performance, where a proposed modified U-Net is used as the encoder. Our dataset consists of novel high-frequency ExactVu ultrasound (US) data collected from 693 patients at five data centers. Gleason Scores (GSs) are assigned to the 12 prostatic regions of each patient. Two classification tasks: benign vs. malignant and low- vs. high-grade, are conducted and the classification results of different prostatic regions are compared. For benign vs. malignant classification, the three-player minimax game framework achieves an Area Under the Receiver Operating Characteristic (AUC) of 93.4%, a sensitivity of 95.1% and a specificity of 87.7%, respectively, representing significant improvements of 5.0%, 3.9%, and 6.0% compared to those of using heterogeneous data, which confirms its effectiveness in terms of PCa classification. [ABSTRACT FROM AUTHOR]

Graphs are commonly used to represent objects, such as images and text, for pattern classification. In a dynamic world, an object may continuously evolve over time, and so does the graph extracted from the underlying object. These changes in graph structure with respect to the temporal order present a new representation of the graph, in which an object corresponds to a set of time-variant graphs. In this paper, we formulate a novel time-variant graph classification task and propose a new graph feature, called a graph-shapelet pattern, for learning and classifying time-variant graphs. Graph-shapelet patterns are compact and discriminative graph transformation subsequences. A graph-shapelet pattern can be regarded as a graphical extension of a shapelet—a class of discriminative features designed for vector-based temporal data classification. To discover graph-shapelet patterns, we propose to convert a time-variant graph sequence into time-series data and use the discovered shapelets to find graph transformation subsequences as graph-shapelet patterns. By converting each graph-shapelet pattern into a unique tokenized graph transformation sequence, we can measure the similarity between two graph-shapelet patterns and therefore classify time-variant graphs. Experiments on both synthetic and real-world data demonstrate the superior performance of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Atrial fibrillation (AF) is one of the most common cardiac arrhythmias, which particularly occurs in the elderly individuals with heart disease. Though AF is often asymptomatic during normal activities, it has huge potential risks for stroke and other severe diseases. Thus, early detection of AF has great importance in the field of public health. Currently, electrocardiography (ECG) is the commonly used measure for the diagnosis of AF, which presents the irregular rhythm of waveform for AF patients. However, the measurement of the ECG signal requires special medical acquisition devices, which are not comfortable for practical monitoring in daily life. In this paper, we explore a very promising algorithm to detect AF from remote face videos by analyzing the color variations of face skin. The main challenge is that the current remote photoplethysmography (rPPG) technique is rather immature, which causes difficulty in extracting accurate pulse signals for describing the cardiac rhythm. To solve this problem, we first utilize various rPPG algorithms to capture pulse rhythms from different regions on the face video. We then investigate biomedical statistical methods to extract suitable features from each pulse signal. Due to the imprecision of video-extracted pulse signals, some traditional physiological features may lose their utility since they were originally proposed for ECG signals. Furthermore, some of them are very susceptible to the influence of noise. Thus, we propose a feature fusion algorithm to select and combine reasonable information from multiple physiological features, which aims to preserve the discriminability of detecting AF in the presence of the noise and outlier disturbances. The experimental results on a real-world database demonstrate the effectiveness of the proposed method in providing useful information for AF detection. [ABSTRACT FROM AUTHOR]

In contrast with nature scenes, aerial scenes are often composed of many objects crowdedly distributed on the surface in bird’s view, the description of which usually demands more discriminative features as well as local semantics. However, when applied to scene classification, most of the existing convolution neural networks (ConvNets) tend to depict global semantics of images, and the loss of low- and mid-level features can hardly be avoided, especially when the model goes deeper. To tackle these challenges, in this paper, we propose a multiple-instance densely-connected ConvNet (MIDC-Net) for aerial scene classification. It regards aerial scene classification as a multiple-instance learning problem so that local semantics can be further investigated. Our classification model consists of an instance-level classifier, a multiple instance pooling and followed by a bag-level classification layer. In the instance-level classifier, we propose a simplified dense connection structure to effectively preserve features from different levels. The extracted convolution features are further converted into instance feature vectors. Then, we propose a trainable attention-based multiple instance pooling. It highlights the local semantics relevant to the scene label and outputs the bag-level probability directly. Finally, with our bag-level classification layer, this multiple instance learning framework is under the direct supervision of bag labels. Experiments on three widely-utilized aerial scene benchmarks demonstrate that our proposed method outperforms many state-of-the-art methods by a large margin with much fewer parameters. [ABSTRACT FROM AUTHOR]