Search

Graph-based clustering plays an important role in the clustering area. Recent studies about graph neural networks (GNN) have achieved impressive success on graph-type data. However, in general clustering tasks, the graph structure of data does not exist such that GNN can not be applied to clustering directly and the strategy to construct a graph is crucial for performance. Therefore, how to extend GNN into general clustering tasks is an attractive problem. In this paper, we propose a graph auto-encoder for general data clustering, AdaGAE, which constructs the graph adaptively according to the generative perspective of graphs. The adaptive process is designed to induce the model to exploit the high-level information behind data and utilize the non-euclidean structure sufficiently. Importantly, we find that the simple update of the graph will result in severe degeneration, which can be concluded as better reconstruction means worse update. We provide rigorous analysis theoretically and empirically. Then we further design a novel mechanism to avoid the collapse. Via extending the generative graph models to general type data, a graph auto-encoder with a novel decoder is devised and the weighted graphs can be also applied to GNN. AdaGAE performs well and stably in different scale and type datasets. Besides, it is insensitive to the initialization of parameters and requires no pretraining. [ABSTRACT FROM AUTHOR]

Graph-based clustering plays an important role in the clustering area. Recent studies about graph neural networks (GNN) have achieved impressive success on graph-type data. However, in general clustering tasks, the graph structure of data does not exist such that GNN can not be applied to clustering directly and the strategy to construct a graph is crucial for performance. Therefore, how to extend GNN into general clustering tasks is an attractive problem. In this paper, we propose a graph auto-encoder for general data clustering, AdaGAE, which constructs the graph adaptively according to the generative perspective of graphs. The adaptive process is designed to induce the model to exploit the high-level information behind data and utilize the non-euclidean structure sufficiently. Importantly, we find that the simple update of the graph will result in severe degeneration, which can be concluded as better reconstruction means worse update. We provide rigorous analysis theoretically and empirically. Then we further design a novel mechanism to avoid the collapse. Via extending the generative graph models to general type data, a graph auto-encoder with a novel decoder is devised and the weighted graphs can be also applied to GNN. AdaGAE performs well and stably in different scale and type datasets. Besides, it is insensitive to the initialization of parameters and requires no pretraining. [ABSTRACT FROM AUTHOR]

Stego-images are often contaminated by interchannel noise or active noise attack when communicating on the Web. And it is challenging to restore embedded image from corrupted stego-image. This paper studies a kNN-bit approximation algorithm to remove noises in embedded image. The proposed algorithm distinguishes reliable bits from extracted bits, and estimates pixel values by keeping reliable bits unchanged and correcting unreliable bits. Specifically, the 8th (highest) unreliable bit of a pixel can be approximated with its nearest neighbor pixels. And then, if an unreliable bit locates at any one of the $5^{th}\sim 7^{th}$ 5 t h ∼ 7 t h bits of a pixel, it is adjusted with two nearest neighbors of the pixel, where the pixel is in-between these two nearest neighbors. Finally, for other unreliable bits, each one is approximated by the maximum and minimum possible values of nearest neighbors of its pixel. We conduct experiments for illustrating the efficiency, and demonstrate that the proposed algorithm can recover the embedded images with good visual quality from corrupted stego-images. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing is an essential research topic for spectral data analysis due to the existence of mixed pixels. Recently, many methods based on sparse nonnegative matrix factorization (NMF) have been widely used for unmixing by incorporating similarity preserving. However, most of them conduct the similarity learning and unmixing by using two separate steps, which may lead to the case that the learned similarity matrix is not the optimal one for unmixing. Thus, the performance of unmixing would be influenced and become undesirable. To alleviate this problem, we propose an adaptive relationship preserving-based sparse NMF (ARP-NMF) for hyperspectral unmixing. Typically, we regard similarity learning and unmixing as an alternative optimization process. During this process, the learned similarity weights and unmixing results can be mutually improved. Thus, our proposed method can learn the optimal similarity weights for unmixing and obtain better generalization ability for different hyperspectral images than traditional methods. Moreover, by using the spectral and spatial local structure, our ARP-NMF method effectively preserves structure consistency between pixels and abundances. Experimental results both on the synthetic data and the real data reveal that our proposed method outperforms several representative sparse NMF-based methods. [ABSTRACT FROM AUTHOR]

Multiview clustering partitions data into different groups according to their heterogeneous features. Most existing methods degenerate the applicability of models due to their intractable hyper-parameters triggered by various regularization terms. Moreover, traditional spectral based methods always encounter the expensive time overheads and fail in exploring the explicit clusters from graphs. In this paper, we present a scalable and parameter-free graph fusion framework for multiview clustering, seeking for a joint graph compatible across multiple views in a self-supervised weighting manner. Our formulation coalesces multiple view-wise graphs straightforward and learns the weights as well as the joint graph interactively, which could actively release the model from any weight-related hyper-parameters. Meanwhile, we manipulate the joint graph by a connectivity constraint such that the connected components indicate clusters directly. The designed algorithm is initialization-independent and time-economical which obtains the stable performance and scales well with the data size. Substantial experiments on toy data as well as real datasets are conducted that verify the superiority of the proposed method compared to the state-of-the-arts over the clustering performance and time expenditure. [ABSTRACT FROM AUTHOR]

Recently, remote sensing image captioning (RSIC) has drawn an increasing attention. In this field, the encoder–decoder-based methods have become the mainstream due to their excellent performance. In the encoder–decoder framework, the convolutional neural network (CNN) is used to encode a remote sensing image into a semantic feature vector, and a sequence model such as long short-term memory (LSTM) is subsequently adopted to generate a content-related caption based on the feature vector. During the traditional training stage, the probability of the target word at each time step is forcibly optimized to 1 by the cross entropy (CE) loss. However, because of the variability and ambiguity of possible image captions, the target word could be replaced by other words like its synonyms, and therefore, such an optimization strategy would result in the overfitting of the network. In this article, we explore the overfitting phenomenon in the RSIC caused by CE loss and correspondingly propose a new truncation cross entropy (TCE) loss, aiming to alleviate the overfitting problem. In order to verify the effectiveness of the proposed approach, extensive comparison experiments are performed on three public RSIC data sets, including UCM-captions, Sydney-captions, and RSICD. The state-of-the-art result of Sydney-captions and RSICD and the competitive results of UCM-captions achieved by TCE loss demonstrate that the proposed method is beneficial to RSIC. [ABSTRACT FROM AUTHOR]

The fusion of hyperspectral (HS) and multispectral (MS) images designed to obtain high-resolution HS (HRHS) images is a very challenging work. A series of solutions has been proposed in recent years. However, the similarity in the structure of the HS image has not been fully used. In this article, we present a novel HS and MS image-fusion method based on nonlocal low-rank tensor approximation and sparse representation. Specifically, the HS image and the MS image are considered the spatially and spectrally degraded versions of the HRHS image, respectively. Then, the nonlocal low-rank constraint term is adopted in order to form the nonlocal similarity and the spatial–spectral correlation. Meanwhile, we add the sparse constraint term to describe the sparsity of abundance. Thus, the proposed fusion model is established and its optimization is solved by alternative direction method of multipliers (ADMM). The experimental results on three synthetic data sets and one real data set show the advantages of the proposed method over several state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

Existing video summarization approaches mainly concentrate on the sequential or structural characteristic of video data. However, they do not pay enough attention to the video summarization task itself. In this article, we propose a meta learning method for performing task-driven video summarization, denoted by MetaL-TDVS, to explicitly explore the video summarization mechanism among summarizing processes on different videos. Particularly, MetaL-TDVS aims to excavate the latent mechanism for summarizing video by reformulating video summarization as a meta learning problem and promote the generalization ability of the trained model. MetaL-TDVS regards summarizing each video as a single task to make better use of the experience and knowledge learned from processes of summarizing other videos to summarize new ones. Furthermore, MetaL-TDVS updates models via a twofold backpropagation, which forces the model optimized on one video to obtain high accuracy on another video in every training step. Extensive experiments on benchmark datasets demonstrate the superiority and better generalization ability of MetaL-TDVS against several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Convolutional Neural Network (CNN) has shown their advantages in salient object detection. CNN can generate great saliency maps because it can obtain high-level semantic information. And the semantic information is usually achieved by stacking multiple convolutional layers and pooling layers. However, multiple pooling operations will reduce the size of the feature map and easily blur the boundary of the salient object. Therefore, such operations are not beneficial to generate great saliency results. To alleviate this issue, we propose a novel edge information-guided hierarchical feature fusion network (HFFNet). Our network fuses features hierarchically and retains accurate semantic information and clear edge information effectively. Specifically, we extract image features from different levels of VGG. Then, we fuse the features hierarchically to generate high-level semantic information and low-level edge information. In order to retain better information at different levels, we adopt a one-to-one hierarchical supervision strategy to supervise the generation of low-level information and high-level information respectively. Finally, we use low-level edge information to guide the saliency map generation, and the edge guidance fusion is able to identify saliency regions effectively. The proposed HFFNet has been extensively evaluated on five traditional benchmark datasets. The experimental results demonstrate that the proposed model is fairly effective in salient object detection compared with 10 state-of-the-art models under different evaluation indicators, and it is superior to most of the comparison models. [ABSTRACT FROM AUTHOR]

Data reconstruction, which aims at preserving statistical properties of the data during the reconstruction has become a new criterion for feature selection. Although feature selection could benefit from the perspective of data reconstruction, it is unable to exploit other crucial information, namely, graph structure and pairwise constraints. To address previously mentioned deficiency, we propose a novel feature selection approach in this paper, known as unsupervised feature selection via data reconstruction and side information. More specifically, the proposed method takes advantage of the prior knowledge regarding pairwise constraints (side information), the minimization of data reconstruction error, and the graph embedding simultaneously, such that pivotal features are selected with preserving data manifold structure. To obtain the robust solution, a robust loss function is applied to the feature selection problem, which interpolates between $\ell _{1}$ -norm and $\ell _{2}$ -norm. Eventually, extensive experiments are conducted to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

People in crowd scenes always exhibit consistent behaviors and form collective motions. The analysis of collective motion has motivated a surge of interest in computer vision. Nevertheless, the effort is hampered by the complex nature of collective motions. Considering the fact that collective motions are formed by individuals, this paper proposes a new framework for both quantifying and detecting collective motion by investigating the spatio-temporal behavior of individuals. The main contributions of this work are threefold: 1) an intention-aware model is built to fully capture the intrinsic dynamics of individuals; 2) a structure-based collectiveness measurement is developed to accurately quantify the collective properties of crowds; 3) a multi-stage clustering strategy is formulated to detect both the local and global behavior consistency in crowd scenes. Experiments on real world data sets show that our method is able to handle crowds with various structures and time-varying dynamics. Especially, the proposed method shows nearly 10% improvement over the competitors in terms of NMI, Purity and RI. Its applicability is illustrated in the context of anomaly detection and semantic scene segmentation. [ABSTRACT FROM AUTHOR]

The existing unsupervised feature extraction methods frequently explore low-redundant features by an uncorrelated constraint. However, the constrained models might incur trivial solutions, due to the singularity of scatter matrix triggered by high-dimensional data. In this paper, we propose a regularized regression model with a generalized uncorrelated constraint for feature selection, which leads to three merits: 1) exploring the low-redundant and discriminative features; 2) avoiding the trivial solutions and 3) simplifying the optimization. Besides that, the local cluster structure is achieved via a novel constrained spectral analysis for the unsupervised learning, where Must-Links and Cannot-Links are transformed into a intrinsic graph and a penalty graph respectively, rather than incorporated into a mixed affinity graph. Accordingly, a discriminative and uncorrelated feature selection with constrained spectral analysis (DUCFS) is proposed with adopting $\sigma $ -norm regularization for interpolating between F-norm and $\ell _{2,1}$ -norm. Due to the flexible gradient and global differentiability, our model converges fast. Extensive experiments on benchmark datasets among several state-of-the-art approaches verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Graph clustering plays an important role in data mining. Based on an input data graph, data points are partitioned into clusters. However, most existing methods keep the data graph fixed during the clustering procedure, so they are limited to exploit the implied data manifold and highly dependent on the initial graph construction. Inspired by the recent development on manifold learning, this paper proposes an Adaptive Consistency Propagation (ACP) method for graph clustering. In order to utilize the features captured from different perspectives, we further put forward the Multi-view version of the ACP model (MACP). The main contributions are threefold: (1) the manifold structure of input data is sufficiently exploited by propagating the topological connectivities between data points from near to far; (2) the optimal graph for clustering is learned by taking graph learning as a part of the optimization procedure; and (3) the negotiation among the heterogeneous features is captured by the multi-view clustering model. Extensive experiments on real-world datasets validate the effectiveness of the proposed methods on both single- and multi-view clustering, and show their superior performance over the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Non-negative Matrix Factorization (NMF) has been one of the most popular clustering techniques in machine leaning, and involves various real-world applications. Most existing works perform matrix factorization on high-dimensional data directly. However, the intrinsic data structure is always hidden within the low-dimensional subspace. And, the redundant features within the input space may affect the final result adversely. In this paper, a new unsupervised matrix factorization method, Discrimination-aware Projected Matrix Factorization (DPMF), is proposed for data clustering. The main contributions are threefold: (1) The linear discriminant analysis is jointly incorporated into the unsupervised matrix factorization framework, so the clustering can be accomplished in the discriminant subspace. (2) The manifold regularization is introduced to perceive the geometric information, and the ${\ell _{2,1}}$ ℓ 2 , 1 -norm is utilized to improve the robustness. (3) An efficient optimization algorithm is designed to solve the proposed problem with proved convergence. Experimental results on one toy dataset and eight real-world benchmarks show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Congestion detection is an important aspect of vehicular management. However, most of the existing algorithms are insufficient for real applications. Traditional features are not discriminative which results in rather poor performance under complex scenarios. The deep features can better represent high-level information, but the training of deep network for regression is difficult. To promote the congestion detection, a robust hierarchical deep learning is proposed for the task. In this method, a deep network is designed for hierarchical semantic feature extraction. Different from traditional deep regression networks, which usually directly utilize mean squared error as loss function, a robust metric learning is employed to effectively train the network. Based on this, multiple networks are combined together to further improve the generalization ability. Extensive experiments are conducted and the proposed model is confirmed to be effective. [ABSTRACT FROM AUTHOR]

How to tackle high dimensionality of data effectively and efficiently is still a challenging issue in machine learning. Identifying anomalous objects from given data has a broad range of real-world applications. Although many classical outlier detection or ranking algorithms have been witnessed during the past years, the high-dimensional problem, as well as the size of neighborhood, in outlier detection have not yet attracted sufficient attention. The former may trigger the distance concentration problem that the distances of observations in high-dimensional space tend to be indiscernible, whereas the latter requires appropriate values for parameters, making models high complex and more sensitive. To partially circumvent these problems, especially the high dimensionality, we introduce a concept called local projection score (LPS) to represent deviation degree of an observation to its neighbors. The LPS is obtained from the neighborhood information by the technique of low-rank approximation. The observation with high LPS is a promising candidate of outlier in high probability. Based on this notion, we propose an efficient and effective outlier detection algorithm, which is also robust to the parameter ${k}$ of ${k}$ nearest neighbors. Extensive evaluation experiments conducted on twelve public real-world data sets with five popular outlier detection algorithms show that the performance of the proposed method is competitive and promising. [ABSTRACT FROM AUTHOR]

Segmentation of the prostate in magnetic resonance image has become more in need for its assistance to diagnosis and surgical planning of prostate carcinoma. Due to the natural variability of anatomical structures, statistical shape model has been widely applied in medical image segmentation. Robust and distinctive local features are critical for statistical shape model to achieve accurate segmentation results. The scale invariant feature transformation (SIFT) has been employed to capture the information of the local patch surrounding the boundary. However, when SIFT feature being used for segmentation, the scale and variance are not specified with the location of the point of interest. To deal with it, the discriminant analysis in machine learning is introduced to measure the distinctiveness of the learned SIFT features for each landmark directly and to make the scale and variance adaptive to the locations. As the gray values and gradients vary significantly over the boundary of the prostate, separate appearance descriptors are built for each landmark and then optimized. After that, a two stage coarse-to-fine segmentation approach is carried out by incorporating the local shape variations. Finally, the experiments on prostate segmentation from MR image are conducted to verify the efficiency of the proposed algorithms. [ABSTRACT FROM PUBLISHER]

Sparse unmixing (SU) algorithms use the existing spectral library as prior knowledge to analyze the endmembers and estimate abundance maps. The majority of SU algorithms use loss functions based on the $L_{2,1}$ -norm or $F$ -norm to minimize reconstruction error. They have different advantages and shortcomings. In short, $F$ -norm has a differentiable characteristic, and it is easy to minimize as a loss function. However, it is very sensitive to heavy noise and outliers. While the $L_{2,1}$ -norm emphasizes the reconstruction error on each band and is robust to noise with different intensities in different bands. But the $L_{2,1}$ -norm is nondifferentiable at zero-point. This article introduces an adaptive loss function based on the $\sigma $ -norm for SU, which combines the advantages of the $L_{2,1}$ -norm and $F$ -norm. The adaptive loss function is related to a nonnegative parameter $\sigma $. By adjusting the parameter $\sigma $ , the adaptive loss function can approach the $F$ -norm or $L_{2,1}$ -norm. To the best of our knowledge, it is the first time to apply an adaptive loss function to SU. Moreover, the adaptive loss function is globally differentiable, and we propose an optimization algorithm for the adaptive loss function and verify its convergence. Experiments on real-world and synthetic HSIs show that the adaptive loss function effectively enhances the performance of the SU algorithms. [ABSTRACT FROM AUTHOR]

Sparse unmixing (SU) is a semisupervised learning problem, which performs abundance estimation when a spectral library is given. In this way, the essence of SU is to select the most suitable subset from the spectral library for representing all mixed pixels. Many SU methods adopt joint-sparse and low-rank constraints to guide the abundance estimation. However, the spatial correlation learning in these algorithms is not accurate enough, which seriously affects the unmixing performance. Besides, most pruning-based unmixing methods suffer from complicated pruning strategies and ignore the relationship between the spectral library and mixed pixels. This article proposes a reweighted low-rank and joint-sparse unmixing approach, which combines an effective pruning strategy (RLSU-LP). The RLSU-LP approach consists of rough unmixing stage, library pruning, and fine-tuning unmixing stage. First, the proposed method utilizes image segmentation to obtain different homogeneous regions, i.e., superpixels. A confidence index is introduced to describe the superpixel homogeneity, which is conducive to learning the meticulous spatial correlation. The RLSU-LP method reasonably relaxes or tightens the sparse and low-rank constraints of the abundance matrix by using the confidence index. Furthermore, a supervised library pruning strategy is proposed, which aims to eliminate the inactive endmembers by considering the contribution of representing mixed pixels. Experiments on the synthesized dataset and authentic hyperspectral images verify the effectiveness of our proposed algorithm. [ABSTRACT FROM AUTHOR]

There are many successful spectral based unsupervised dimensionality reduction methods, including Laplacian Eigenmap (LE), Locality Preserving Projection (LPP), Spectral Regression (SR), etc. We find that LPP and SR are equivalent if the symmetric similarity matrix is doubly stochastic, Positive Semi-Definite (PSD) and with rank $p$ p , where $p$ p is the reduced dimension. Since solving SR is believed faster than solving LPP based on some related literature, the discovery promotes us to seek to construct such specific similarity matrix to speed up LPP solving procedures. We then propose an unsupervised linear method called Unsupervised Large Graph Embedding (ULGE). ULGE starts with a similar idea as LPP but adopts an efficient approach to construct anchor-based similarity matrix and then performs spectral analysis on it. Moreover, since conventional anchor generation strategies suffer kinds of problems, we propose an efficient and effective anchor generation strategy, called Balanced $K$ K -means based Hierarchical $K$ K -means (BHKH). The computational complexity of ULGE can reduce to $O(ndm)$ O (n d m) , which is a significant improvement compared to conventional methods need $O(n^2d)$ O (n 2 d) at least, where $n$ n , $d$ d and $m$ m are the number of samples, dimensions, and anchors, respectively. Extensive experiments on several publicly available datasets demonstrate the efficiency and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Deep learning-based hyperspectral image superresolution methods have achieved great success recently. However, most methods utilize 2D or 3D convolution to explore features, and rarely combine the two types of convolution to design networks. Moreover, when the model only contains 3D convolution, almost all the methods take all the bands of hyperspectral image as input to analyze, which requires more memory footprint. To address these issues, we explore a new structure for hyperspectral image superresolution using spectrum and feature context. Inspired by the high similarity among adjacent bands, we design a dual-channel network through 2D and 3D convolution to jointly exploit the information from both single band and adjacent bands, which is different from previous works. Under the connection of depth split, it can effectively share spatial information so as to improve the learning ability of 2D spatial domain. Besides, our method introduces the features extracted from previous band, which contributes to the complementarity of information and simplifies the network structure. Through feature context fusion, it significantly enhances the performance of the algorithm. Extensive evaluations and comparisons on three public datasets demonstrate that our approach produces the state-of-the-art results over the existing approaches. [ABSTRACT FROM AUTHOR]

Hyperspectral image super-resolution (SR) methods based on deep learning have achieved significant progress recently. However, previous methods lack the joint analysis between spectrum and horizontal or vertical direction. Besides, when both 2D and 3D convolution are in the network, the existing models cannot effectively combine the two. To address these issues, in this article, we propose a novel hyperspectral image SR method by exploring the relationship between 2D/3D convolution (ERCSR). Our method alternately employs 2D and 3D units to solve the problem of structural redundancy by sharing spatial information during reconstruction for existing model, which can enhance the learning ability of 2D spatial domain. Importantly, compared with the network using 3D units, i.e., 2D units are replaced by 3D units, it can not only reduce the size of the model but also improve the performance of the model. Furthermore, to exploit the spectrum fully, the split adjacent spatial and spectral convolution (SAEC) is designed to parallelly explore information between spectrum and horizontal or vertical direction in space. Experiments on widely used benchmark datasets demonstrate that the proposed approach outperforms state-of-the-art SR algorithms across different scales in terms of quantitative and qualitative analysis. [ABSTRACT FROM AUTHOR]

Hyperspectral images can provide dozens to hundreds of continuous spectral bands, so the richness of information has been greatly improved. However, these bands lead to increasing complexity of data processing, and the redundancy of adjacent bands is large. Recently, although many band selection methods have been proposed, this task is rarely handled through the context information of the whole spectral bands. Moreover, the scholars mainly focus on the different numbers of selected bands to explain the influence by accuracy measures, neglecting how many bands to choose is appropriate. To tackle these issues, we propose a fast neighborhood grouping method for hyperspectral band selection (FNGBS). The hyperspectral image cube in space is partitioned into several groups using coarse-fine strategy. By doing so, it effectively mines the context information in a large spectrum range. Compared with most algorithms, the proposed method can obtain the most relevant and informative bands simultaneously as subset in accordance with two factors, such as local density and information entropy. In addition, our method can also automatically determine the minimum number of recommended bands by determinantal point process. Extensive experimental results on benchmark data sets demonstrate the proposed FNGBS achieves satisfactory performance against state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Multi-Task Learning attempts to explore and mine the sufficient information within multiple related tasks for the better solutions. However, the performance of the existing multi-task approaches would largely degenerate when dealing with the polluted data, i.e., outliers. In this paper, we propose a novel robust multi-task model by incorporating a flexible manifold constraint (FMC-MTL) and a robust loss. Specifically speaking, multi-task subspace is embedded with a relaxed and generalized Stiefel Manifold for considering point-wise correlation and preserving the data structure simultaneously. In addition, a robust loss function is developed to ensure the robustness to outliers by smoothly interpolating between ℓ2,1-norm and squared Frobenius norm. Equipped with an efficient algorithm, FMC-MTL serves as a robust solution to tackling the severely polluted data. Moreover, extensive experiments are conducted to verify the superiority of our model. Compared to the state-of-the-art multi-task models, the proposed FMC-MTL model demonstrates remarkable robustness to the contaminated data. [ABSTRACT FROM AUTHOR]

Many representation methods were built for gray image textures. However, they are not effective for color textures in general. To alleviate this problem, in this paper we propose a novel Compact Interchannel Sampling Difference Descriptor (CISDD) for color texture classification. In particular, considering sampling-based method can capture more directional information, we first use a heavy-tailed distribution, t-distribution to generate sample points in the image patch to calculate the micro-block difference. Then we model the interchannel relationship of color texture image by using dense micro-block differences. Furthermore, we utilize principal component analysis (PCA) to reduce the dimensions of the features encoded by the Fisher vector, and construct a Compact Interchannel Sampling Difference Descriptor (CISDD) for representing color texture image. Finally, experimental results on five published standard texture datasets (KTH-TIPS, VisTex, CUReT, USPTex and Colored Brodatz) reveal that CISDD is effective and outperforms thirteen representative color texture classification methods. [ABSTRACT FROM AUTHOR]

Unsupervised feature selection has attracted more and more attention due to the rapid growth of the large amount of unlabelled and high-dimensional data. The performance of traditional spectral-based unsupervised methods always depends on the quality of constructed similarity matrix. However, real world data always contain a large number of noise samples and features that make the similarity matrix created by original data cannot be fully relied. We propose an unsupervised feature selection method which conducts feature selection and local structure learning simultaneously. Moreover, we add an important constraint on the similarity matrix to allow it to capture more accurate information of the data structure. To perform feature selection, orthogonal constraint and ℓ2,p-norm are adopted on the projection matrix. An efficient and simple algorithm is derived to tackle the problem. We conduct comprehensive experiments on various benchmark data sets, including handwritten digit, face image, and biomedical data, to validate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

As a fundamental and challenging task in bridging language and vision domains, Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality, and its key challenge is to measure the semantic similarity across different modalities. Although significant progress has been achieved, existing approaches typically suffer from two major limitations: (1) It hurts the accuracy of the representation by directly exploiting the bottom-up attention based region-level features where each region is equally treated. (2) It limits the scale of negative sample pairs by employing the mini-batch based end-to-end training mechanism. To address these limitations, we propose a Unified Semantic Enhancement Momentum Contrastive Learning (USER) method for ITR. Specifically, we delicately design two simple but effective Global representation based Semantic Enhancement (GSE) modules. One learns the global representation via the self-attention algorithm, noted as Self-Guided Enhancement (SGE) module. The other module benefits from the pre-trained CLIP module, which provides a novel scheme to exploit and transfer the knowledge from an off-the-shelf model, noted as CLIP-Guided Enhancement (CGE) module. Moreover, we incorporate the training mechanism of MoCo into ITR, in which two dynamic queues are employed to enrich and enlarge the scale of negative sample pairs. Meanwhile, a Unified Training Objective (UTO) is developed to learn from mini-batch based and dynamic queue based samples. Extensive experiments on the benchmark MSCOCO and Flickr30K datasets demonstrate the superiority of both retrieval accuracy and inference efficiency. For instance, compared with the existing best method NAAF, the metric R@1 of our USER on the MSCOCO 5K Testing set is improved by 5% and 2.4% on caption retrieval and image retrieval without any external knowledge or pre-trained model while enjoying over 60 times faster inference speed. Our source code will be released at https://github.com/zhangy0822/USER. [ABSTRACT FROM AUTHOR]

Over the past few years making use of deep networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), classifying hyperspectral images has progressed significantly and gained increasing attention. In spite of being successful, these networks need an adequate supply of labeled training instances for supervised learning, which, however, is quite costly to collect. On the other hand, unlabeled data can be accessed in almost arbitrary amounts. Hence it would be conceptually of great interest to explore networks that are able to exploit labeled and unlabeled data simultaneously for hyperspectral image classification. In this article, we propose a novel graph-based semisupervised network called nonlocal graph convolutional network (nonlocal GCN). Unlike existing CNNs and RNNs that receive pixels or patches of a hyperspectral image as inputs, this network takes the whole image (including both labeled and unlabeled data) in. More specifically, a nonlocal graph is first calculated. Given this graph representation, a couple of graph convolutional layers are used to extract features. Finally, the semisupervised learning of the network is done by using a cross-entropy error over all labeled instances. Note that the nonlocal GCN is end-to-end trainable. We demonstrate in extensive experiments that compared with state-of-the-art spectral classifiers and spectral–spatial classification networks, the nonlocal GCN is able to offer competitive results and high-quality classification maps (with fine boundaries and without noisy scattered points of misclassification). [ABSTRACT FROM AUTHOR]

Band selection is one of the most important technique in the reduction of hyperspectral image (HSI). Different from traditional feature selection problem, an important characteristic of it is that there is usually strong correlation between neighboring bands, that is, bands with close indexes. Aiming to fully exploit this prior information, a novel band selection method called optimal neighborhood reconstruction (ONR) is proposed. In ONR, band selection is considered as a combinatorial optimization problem. It evaluates a band combination by assessing its ability to reconstruct the original data, and applies a noise reducer to minimize the influence of noisy bands. Instead of using some approximate algorithms, ONR exploits a recurrence relation that underlies the optimization target to obtain the optimal solution in an efficient way. Besides, we develop a parameter selection approach to automatically determine the parameter of ONR, ensuring it is adaptable to different data sets. In experiments, ONR is compared with some state-of-the-art methods on six HSI data sets. The results demonstrate that ONR is more effective and robust than the others in most of the cases. [ABSTRACT FROM AUTHOR]

Crowd counting from a single image is a challenging task due to high appearance similarity, perspective changes, and severe congestion. Many methods only focus on the local appearance features and they cannot handle the aforementioned challenges. In order to tackle them, we propose a perspective crowd counting network (PCC Net), which consists of three parts: 1) density map estimation (DME) focuses on learning very local features of density map estimation; 2) random high-level density classification (R-HDC) extracts global features to predict the coarse density labels of random patches in images; and 3) fore-/background segmentation (FBS) encodes mid-level features to segments the foreground and background. Besides, the Down, Up, Left, and Right (DULR) module is embedded in PCC Net to encode the perspective changes on four directions (DULR). The proposed PCC Net is verified on five mainstream datasets, which achieves the state-of-the-art performance on the one and attains the competitive results on the other four datasets. The source code is available at https://github.com/gjy3035/PCC-Net. [ABSTRACT FROM AUTHOR]