Search

Object detection is a basic vision task that accompanies people's daily lives all the time. The development of object detection technology has experienced an evolution from traditional-based algorithms to deep learning-based algorithms, which has made a qualitative leap in both detection accuracy and detection speed. With the advancement of deep learning, object detection techniques are increasingly becoming a part of everyday life, with the YOLO series of algorithms being extensively applied in various industries. In this paper, we initially present the frequently utilized datasets and evaluation criteria for object detection. Subsequently, we delve into the evolution of traditional object detection algorithms, highlighting two-stage and one-stage approaches through illustrative examples of classical methods. We also conduct a comprehensive summary and analysis of the detection results obtained by these methods. In addition, we introduce object detection applications in daily life, as well as the importance and some difficulties of these applications. Finally, we analyze and summarize the difficulties and challenges facing the task of object detection, and we look forward to the future development direction of object detection. • This survey is an extended version of our paper in ICIC2023. • We review the development and challenges of object detection. • We present the application of object detection and make prospects for the future. [ABSTRACT FROM AUTHOR]

Single-object tracking is regarded as a challenging task in computer vision, especially in complex spatio-temporal contexts. The changes in the environment and object deformation make it difficult to track. In the last 10 years, the application of correlation filters and deep learning enhances the performance of trackers to a large extent. This paper summarizes single-object tracking algorithms based on correlation filters and deep learning. Firstly, we explain the definition of single-object tracking and analyze the components of general object tracking algorithms. Secondly, the single-object tracking algorithms proposed in the past decade are summarized according to different categories. Finally, this paper summarizes the achievements and problems of existing algorithms by analyzing experimental results and discusses the development trends. [ABSTRACT FROM AUTHOR]

Deep learning technologies have been rapidly developing recently. They have shown excellent performances in many fields. However, deep learning networks have weak adaptability to small sample sizes.Usually, deep learning networks require tens of thousands of samples to avoid overfitting. In contrast, the kernel method can deal with small sample sizes. In this paper, we use only dozens of samples to train a successful classifier. Deep multiple kernel learning (DMKL) has emerged in recent years. It combines the ideas of deep learning and multiple kernel learning. Unfortunately, the DMKL network with a fixed structure cannot adapt to data of different dimensions and sizes. Therefore, in this paper, we propose a novel depth-width-scaling multiple kernel learning (DWS-MKL) algorithm. It has the ability to adjust the architecture according to the input data. We optimize the estimation of leave-one-out error by using the span bound instead of the dual objective function. Finally, we choose a large number of data sets from the UCI benchmark data sets for classification tasks. We also evaluate DWS-MKL on the MNIST data set. The experimental results show that different frameworks have different performances on the same dataset. Our DWS-MKL algorithm obtains better classification results than the state-of-the-art kernel learning algorithms, as determined by a thorough comparison. The encouraging results demonstrate that our method has the potential to improve generalization performance of the model. [ABSTRACT FROM AUTHOR]

Deep image clustering networks have the capability to categorize unlabeled images, thereby effectively utilizing them. This paper synthesizes recent researches about deep image clustering network and summarizes them within a general framework. Image Preprocessing part transforms collected images into a dataset accepted by the network, then Image Embedding part embeds images from the dataset into vectors which represents image features. After Feature Processing part further reduces the dimensionality or enhances these features, the following Feature Clustering part divides the images into several categories. Cluster Result Processing part treats the clustering outcomes to implement weighted, multi-view, subspace, multimodal, or self-supervised methods. Downstream Applications part employ the clustering results to address various real-world problems. The performance of common baseline clustering methods and several feature extraction architectures are also compared and analyzed. The results indicate that within deep image clustering networks, the choice of clustering algorithm has a relatively minor impact on clustering performance, whereas the selection of the feature extraction network architecture is decisive for clustering metrics. The choice of architecture should be customized based on the characteristics of the dataset. Finally, we provide suggestions for potential research directions in deep image clustering networks. • Analyzes deep image clustering theory, its performance benefits, and limitations. • Summarizes recent deep image clustering improvements with experimental data analysis. • Introduces deep image clustering applications and future improvement prospects. [ABSTRACT FROM AUTHOR]

Motion blur can easily affect the quality of images. For example, Quick Response (QR) code is hard to be identified with severe motion blur caused by camera shaking or object moving. In this paper, a motion blur QR code identification algorithm based on feature extraction and improved adaptive thresholding is proposed. First, this work designs a feature extraction framework using a deep convolutional network for motion deblurring. The framework consists of a basic end-to-end network for feature extraction, an encoder-decoder structure for increasing training feasibility and several ResBlocks for producing large receptive fields. Then an improved adaptive thresholding method is used to avoid influence caused by uneven illumination. Finally, the proposed algorithm is compared with several recent methods on a dataset including QR code images influenced by both motion blur and uneven illumination. Experimental results demonstrate that the processing time and identification accuracy of the proposed algorithm are improved in executing motion blur QR code identification missions compared with other competing methods. [ABSTRACT FROM AUTHOR]

With the increasing maturity of convolution neural network (CNN) technology, the image super-resolution reconstruction (SR) method based on CNN is booming and has achieved many remarkable results. Undoubtedly, SR has become the mainstream direction of image reconstruction technology. However, most of the existing SR methods improve the reconstruction performance by increasing the depth of networks, which also increases the number of parameters, number of network computations, and difficulty of training network. To solve the performance complexity dilemma in SR, this paper proposes a network called a multi-scale dense recursive fusion network (MSDRFN). The network is composed of three parts: initial feature extraction module, multi-scale dense fusion group module and recursive reconstruction module. In detail, rough features are first extracted through a shallow feature extraction module, and then are inputted into multi-scale dense fusion blocks (MSDFBs) group. Each MSDFB makes full use of image features in convolution kernels of different sizes to obtain different hierarchical features, and further these output features are inputted into the channel attention mechanism to learn their corresponding weights. All MSDFBs outputs will be restored to high resolution images via the recursive reconstruction module. In addition, the network supplements the information loss with residual learning, which is embodied in one long-jump connection and several short-jump connections. The proposed network is mainly trained in the Pytorch deep learning framework. In comparison experiments on benchmark datasets, the proposed method outperformed the most advanced convolutional methods. [ABSTRACT FROM AUTHOR]

An important objective in computer vision is to analyze multiple images and subsequently reconstruct the shape and structure in 3D. Traditional multi-view 3D reconstruction techniques extract and match key features from images with known camera parameters. However, this approach is inefficient and fails to fully exploit the advantages of multi-view information. Advancements in deep learning have revolutionized multi-view 3D reconstruction by enabling end-to-end 3D shape inferencing without the need for sequential feature matching typically found in conventional algorithms. Recent rapid progress in this field necessitates a thorough review of current algorithms and provide insight into method of improving 3D reconstruction performance. This review classifies reconstruction algorithms according to their resultant model, including depth map, voxel, point cloud, mesh, and implicit surface. Additionally, this review encompasses the inclusion of frequently employed network training loss functions for network training, assessment metrics, and the incorporation of 3D datasets. Experimental results are also presented to assess the performance of different algorithms. Finally, the paper concludes with a summary, discussion of challenges, and potential future directions. [ABSTRACT FROM AUTHOR]

Recently, the Extreme Learning Machine (ELM) algorithm has been applied to various fields due to its rapidity and significant generalization performance. Traditionally, deep learning (DL) and wavelet neural networks (WNN) methods reach a high classification accuracy in machine learning applications. As a result, a new structure based on WNN, deep architecture and ELM is proposed in this paper. The proposed method is based on Extreme Learning Machine Auto-Encoder with DL structure and a composite wavelet activation function used in the hidden nodes. To evaluate the performance of our approach, we used standard benchmark data-sets, namely COIL-20, Pima Indian Diabetes (PID), MNIST and EMNIST. Experimental results show that our method offers satisfactory results and performance compared to other approaches. [ABSTRACT FROM AUTHOR]

As one of the core technologies of the automatic control system for unmanned surface vehicles (USVs), autonomous collision avoidance algorithm is the key to ensure the safe navigation of USVs. In this paper, path planning and dynamic collision avoidance (PPDC) algorithm which obeys COLREGs is proposed for USVs. In order to avoid unnecessary collision avoidance actions, the risk assessment model is developed, which is used to determine the switching time of path planning and dynamic collision avoidance. In order to train the algorithm which complies with the COLREGs, the encounter situation is divided quantitatively, which is regarded as the input state of the system, so that the high-dimensional input is successfully avoided. The state space of the USV is defined by relative parameters to improve the generalization ability of the algorithm, meanwhile, a network structure based on DDPG is designed to achieve the continuous output of thrust and rudder angle. Combined with path planning, collision avoidance, compliance with COLREGs and smooth arrival task, four kinds of reward functions are designed. In order to solve the problem of low training efficiency of experience replay mechanism in DDPG, cumulative priority sampling mechanism is proposed. Through the simulation and verification in a variety of scenarios, it is proved that PPDC algorithm has the function of path planning and dynamic collision avoidance in compliance with COLREGs, which has good real-time performance and security. [ABSTRACT FROM AUTHOR]

The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous driving. This paper studies monocular VO from the perspective of Deep Learning (DL). Unlike most current learning-based methods, our approach, called DeepAVO, is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we present a novel four-branch network to learn the rotation and translation by leveraging Convolutional Neural Networks (CNNs) to focus on different quadrants of optical flow input. To enhance the ability of feature selection, we further introduce an effective channel-spatial attention mechanism to force each branch to explicitly distill related information for specific Frame to Frame (F2F) motion estimation. Experiments on various datasets involving outdoor driving and indoor walking scenarios show that the proposed DeepAVO outperforms the state-of-the-art monocular methods by a large margin, demonstrating competitive performance to the stereo VO algorithm and verifying promising potential for generalization. [ABSTRACT FROM AUTHOR]

Deep learning is an effective tool to assist doctors with many time-consuming and error-prone medical image analytical tasks. However, deep models are shown to be vulnerable to adversarial attacks, posing significant challenges to clinical applications. Existing works regarding the robustness of deep learning models are scarce, where most of them focus on the attack of medical image classification models. In this paper, a differential evolution attack (DEAttack) method is proposed to generate adversarial examples for medical image segmentation models. Our method does not require extra information such as the network's structures and weights compared with the most widely investigated gradient-based attack methods. Additionally, benefit from the embedded differential evolution algorithm, which can preserve diversities of the optimization space. The proposed method can achieve better results than gradient-based methods, which can successfully attack the segmentation model with only perturbing a small fraction of the image pixels, demonstrating that the medical image segmentation model is more susceptible to adversarial examples. In addition to evaluating model robustness attack with public datasets, our DEAttack method was also tested on the clinical diagnostic dataset, demonstrating its superior performance and elegant process for the robustness evaluation of deep models in medical image segmentation. [ABSTRACT FROM AUTHOR]

Many RGBT trackers utilize adaptive weighting mechanism to treat dual modalities differently and obtain more robust feature representations for tracking. Although these trackers work well under certain conditions, however, they ignore the information interactions in feature learning, which might limit tracking performance. In this paper, we propose a novel cross-modality message passing model to interactively learn robust deep representations of dual modalities for RGBT tracking. Specifically, we extract features of dual modalities by backbone network and take each channel of these features as a node of a graph. Therefore, all channels of dual modalities can explicitly communicate with each other by the graph learning, and the outputted features are thus more diverse and discriminative. Moreover, we introduce the gate mechanism to control the propagation of information flow to achieve more intelligent fusion. The features generated from the interactive cross-modality message passing model will be passed selectively through the gate layer and concatenated with original features as the final representation. We extend the ATOM tracker into its dual-modality version and combine it with our proposed module for final tracking. Extensive experiments on two RGBT benchmark datasets validate the effectiveness and efficiency of our proposed algorithm. [ABSTRACT FROM AUTHOR]

Lossy image compression is likely to produce blurred images which leads to erroneous image-level understanding. The human visual system (HVS) is focused on the area of interest present in the image. Motivated by this fact, we propose a compression-decompression algorithm focusing on the important content present in different parts of the image. Using the concept of the Guided Grad-CAM (Gradient-weighted Class Activation Mapping) technique to produce heat maps with the help of a heat map generator trained on ResNet-50, a saliency-guided encoding–decoding algorithm is developed. A wider multi-scale saliency guided convolutional neural network (MsSG-CNN) is designed, in which the notion of convolution with different size filters helps to obtain unique but different features. The feature extraction followed by multilevel fusion of features helps deep neural network (DNN) to capture contextual information and obtain high quality, good resolution, visually pleasing images with fine details. The proposed algorithm is tested on the Kodak benchmark dataset, CLIC 2019 challenging dataset, and FDDB facial images dataset. At low bit rates, the MS-SSIM of the proposed algorithm is found to be superior to JPEG, JPEG2000, BPG, WebP, and Minnen's approaches with approximately up to 60%, 24.80%, 11.43%, 23.08% & 75% gains respectively, which is quite a significant improvement, when tested on the Kodak dataset. Similarly, at high bit rates, the improvement in MS-SSIM is approximately up to 41.67%, 37.30%, 23.90% 34.21% & 13.33% when compared with JPEG, JPEG2000, BPG, WebP, and Minnen's approaches respectively. The improvement in PSNR at low and high bit rates is approximately up to 11.32%, 5%, 5.26% and 5.6%, 10.29%, 8.7% as compared to JPEG, Balle's, and Lee's algorithms respectively. The PSNR-HVS has been improved by approximately up to 27.27%, 19.15%, and 28.33%, 28% as compared to JPEG and Toderici's algorithms respectively at low and high bit-rates. A similar type of improvement is obtained with FDDB and CLIC 2019 datasets also, which is discussed in the paper. [ABSTRACT FROM AUTHOR]

• An algorithm that transforms long-tailed problem into hierarchical learning problem. • An effective knowledge transfer paradigm is proposed to help hierarchical learning. • The performance of our model outperforms the state-of-the-art methods. Deep visual recognition methods have achieved excellent performance on artificially constructed image datasets where the data distribution is balanced. However, in real-world scenarios, data distribution is usually extremely imbalanced and exhibit a long-tailed distribution where data in each head class is more than the class in the tail. Many efficient deep learning methods fail to work normally, i.e., they perform well in the head class while poor in the tail class. In this paper, we propose a two-layer Hierarchical-Learning Long-Tailed Recognition (HL-LTR) algorithm which transforms the long-tailed problem into a hierarchical classification problem by constructing a hierarchical superclass tree in which each layer corresponds to a recognition task. In the first layer of the tree, the degree of data imbalance is largely decreased. The recognition task of the second layer is the original long-tailed recognition problem. The training of HL-LTR is top-down. The knowledge learned by the first layer transfers to classes of the second layer and guides the feature learning of the second layer by using attention mechanism module and knowledge distillation method. Compared with directly solving the most difficult long-tailed recognition task, HL-LTR achieves better performance due to its progressive learning method from easy to difficult and effective knowledge transfer strategy. [ABSTRACT FROM AUTHOR]

Lossy image compression is likely to produce blurred images which leads to erroneous image-level understanding. The human visual system (HVS) is focused on the area of interest present in the image. Motivated by this fact, we propose a compression-decompression algorithm focusing on the important content present in different parts of the image. Using the concept of the Guided Grad-CAM (Gradient-weighted Class Activation Mapping) technique to produce heat maps with the help of a heat map generator trained on ResNet-50, a saliency-guided encoding–decoding algorithm is developed. A wider multi-scale saliency guided convolutional neural network (MsSG-CNN) is designed, in which the notion of convolution with different size filters helps to obtain unique but different features. The feature extraction followed by multilevel fusion of features helps deep neural network (DNN) to capture contextual information and obtain high quality, good resolution, visually pleasing images with fine details. The proposed algorithm is tested on the Kodak benchmark dataset, CLIC 2019 challenging dataset, and FDDB facial images dataset. At low bit rates, the MS-SSIM of the proposed algorithm is found to be superior to JPEG, JPEG2000, BPG, WebP, and Minnen's approaches with approximately up to 60%, 24.80%, 11.43%, 23.08% & 75% gains respectively, which is quite a significant improvement, when tested on the Kodak dataset. Similarly, at high bit rates, the improvement in MS-SSIM is approximately up to 41.67%, 37.30%, 23.90% 34.21% & 13.33% when compared with JPEG, JPEG2000, BPG, WebP, and Minnen's approaches respectively. The improvement in PSNR at low and high bit rates is approximately up to 11.32%, 5%, 5.26% and 5.6%, 10.29%, 8.7% as compared to JPEG, Balle's, and Lee's algorithms respectively. The PSNR-HVS has been improved by approximately up to 27.27%, 19.15%, and 28.33%, 28% as compared to JPEG and Toderici's algorithms respectively at low and high bit-rates. A similar type of improvement is obtained with FDDB and CLIC 2019 datasets also, which is discussed in the paper. [ABSTRACT FROM AUTHOR]

• Developing an under-clustering algorithm to extract the most possible clusters. • Involving heuristics and deep models in the framework for clustering effectiveness. • Making up the deep learning research gap in the field of plant disease annotation. Current annotation for plant disease images depends on manual sorting and handcrafted features by agricultural experts, which is time-consuming and labour-intensive. In this paper, we propose a self-supervised clustering framework for grouping plant disease images based on the vulnerability of Kernel K-means. The main idea is to establish a cross iterative under-clustering algorithm based on Kernel K-means to produce the pseudo-labeled training set and a chaotic cluster to be further classified by a deep learning module. In order to verify the effectiveness of our proposed framework, we conduct extensive experiments on three different plant disease datatsets with five plants and 17 plant diseases. The experimental results show the high superiority of our method to do image-based plant disease classification over balanced and unbalanced datasets by comparing with five state-of-the-art existing works in terms of different metrics. [ABSTRACT FROM AUTHOR]

Deep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour have been long standing issues in DQNs. The unstable behaviour is often characterised by overestimation in the Q -values, commonly referred to as the overestimation bias. To address the overestimation bias and the divergent behaviour, a number of heuristic extensions have been proposed. Notably, multi-step updates have been shown to drastically reduce unstable behaviour while improving agent's training performance. However, agents are often highly sensitive to the selection of the multi-step update horizon (n), and our empirical experiments show that a poorly chosen static value for n can in many cases lead to worse performance than single-step DQN. Inspired by the success of n -step DQN and the effects that multi-step updates have on overestimation bias, this paper proposes a new algorithm that we call 'Elastic Step DQN' (ES-DQN) to alleviate overestimation bias in DQNs. ES-DQN dynamically varies the step size horizon in multi-step updates based on the similarity between states visited. Our empirical evaluation shows that ES-DQN out-performs n -step with fixed n updates, Double DQN and Average DQN in several OpenAI Gym environments while at the same time alleviating the overestimation bias. [ABSTRACT FROM AUTHOR]

Deep learning algorithms are a subset of the machine learning algorithms, which aim at discovering multiple levels of distributed representations. Recently, numerous deep learning algorithms have been proposed to solve traditional artificial intelligence problems. This work aims to review the state-of-the-art in deep learning algorithms in computer vision by highlighting the contributions and challenges from over 210 recent research papers. It first gives an overview of various deep learning approaches and their recent developments, and then briefly describes their applications in diverse vision tasks, such as image classification, object detection, image retrieval, semantic segmentation and human pose estimation. Finally, the paper summarizes the future trends and challenges in designing and training deep neural networks. [ABSTRACT FROM AUTHOR]

Predicting depth from an image is an essential problem in the area of scene understanding and deep learning shows great potential in this area. Unsupervised methods regard image reconstruction loss as the supervised information which shows a great potential of application. Most methods face the problem that their depth estimation results are not accurate enough for detailed autopilot scenarios, which will limit its application. These methods are often based on the fully convolutional neural network, which is the most commonly used network in the image-to-image field. In this paper, aiming at optimizing the depth estimation network architecture, we propose two networks that fuse the features of different encoding layers for monocular depth estimation, a multilayer information fusion U-Net (FU-Net) and a more lightweight one (LFU-Net). In order to improve the efficiency of feature fusion, we propose a hybrid attention mechanism to optimize our network and named it as AgFU-Net. We compare our networks with other improvements of U-Net, and the result shows that our networks are more efficient. Also, the loss function is fine-tuned for the unsupervised depth estimation algorithm. Our improvements achieve results that are comparable with state-of-the-art unsupervised monocular depth prediction methods on the KITTI benchmarks. [ABSTRACT FROM AUTHOR]

In the coming era of big data, many advances and attempts have been witnessed in deep learning based remaining useful life (RUL) prediction methods which can construct the mapping relation between the massive information and the RUL. Existing studies leverage advanced deep networks for RUL prediction mainly generating the point estimates for the RUL while the prognostic uncertainty quantification is often difficult. However, it is well admitted that such prognostic uncertainty quantification is important and cannot be neglected for health management of degrading products. The purpose of this paper is to develop an adaptive prognostic method towards both the massive data and prognostics uncertainty by leveraging the advantages of deep learning methods in processing massive data and stochastic methods in the uncertainty representation. To do so, a continuous deep belief network (CDBN) is first utilized to extract the deep hidden features behind the massive information, and then, we determine the health index via the self-organizing map (SOM) neural network based on the extracted features. Next, the diffusion process is applied to construct the health index evolving model. The parameters in the diffusion process are estimated online by combining Bayesian method and Expectation Maximization (EM) algorithm. Consequently, the probability density function (PDF) of the RUL can be obtained and updated adaptively. Finally, a practical case study for bearings is provided to substantiate the effectiveness and superiority of the proposed method. Experimental results indicate that the proposed method can provide more accurate RUL predictions. [ABSTRACT FROM AUTHOR]

Inductive Venn-ABERS predictors (IVAPs) are a type of probabilistic predictors with the theoretical guarantee that their predictions are perfectly calibrated. In this paper, we propose to exploit this calibration property for the detection of adversarial examples in binary classification tasks. By rejecting predictions if the uncertainty of the IVAP is too high, we obtain an algorithm that is both accurate on the original test set and resistant to adversarial examples. This robustness is observed on adversarials for the underlying model as well as adversarials that were generated by taking the IVAP into account. The method appears to offer competitive robustness compared to the state-of-the-art in adversarial defense yet it is computationally much more tractable. [ABSTRACT FROM AUTHOR]

Deep learning is a branch of neural network which has been intensively developed in the last decade. Due to the high-accuracy classification ability, the deep learning algorithms have been widely used in many fields, such as speech recognition, image recognition, and natural speech processing. However, they also show some shortcomings especially on the selection of some parameters in the network, including hyper-parameters, which is still treated as a time consuming task. In this paper, a modified ABC (ABC-ISB) optimization algorithm is proposed to automatically train the parameters of Feed-Forward Artificial Neural Networks, which is a typical a neural network. In the proposed ABC algorithm, we utilize the information of neighbors with better performance to accelerate the convergence of employed and onlooker bees respectively. In addition, a new selection strategy and a gbest-guided strategy are introduced to enhance the global search capability and balance the exploration and exploitation of the algorithm separately. The experimental results show our ABC-ISB is generally leading and competitive. [ABSTRACT FROM AUTHOR]

• Presenting a new deep transfer algorithm for cross-domain Image classification. • Proposing a novel domain adaptation approach based on the attribute learning. • Exploring the structural relationship of the sample features rather than simply learning the features of input samples. • Experiments are employed and show the usefulness of the proposed method. Domain adaptation aims at improving the performance on an unknown target domain by transferring the knowledge learned from a related source domain. In this paper, we propose a structural attribute learning network (SAL Net) which can learn transferable domain-invariance features based on the attribute learning. Our proposed SAL Net can learn both the deep visual features which describe the appearance of objects and the semantic attribute features which are robust to the domain shift. To promote the adaptation performance, we construct a structural graph of the visual and semantic attributes by a graph convolutional network(GCN). Our structural attribute learning framework not only learns the domain-invariant attribute features but also extracts the relationship of the features. We perform a set of comparative experiments on the standard domain adaptation benchmarks. The results demonstrate that our proposed method outperforms the previous adaptation methods. [ABSTRACT FROM AUTHOR]

For solving the vehicle Re-identification (Re-ID) task, we need to focus our attention on the details with arbitrary size in the image, and it's tough to locate these details accurately. In this paper, we propose a Multi-Attention Deep Reinforcement Learning (MADRL) model to focus on multi-attentional subregions that spreading randomly in the image, and extract the discriminative features for the Re-ID task. First, we obtain multiple attentions from the representative features, then group the feature channels into different parts, then train a deep reinforcement learning model to learn more accurate positions of these fine-grained details with different losses. Unlike existing models with complex strategies to keep the patch-matching constrains, our MADRL model can automatically locate the matching patches (multi-attentional subregions) in different vehicle images with the same identification (ID). Furthermore, based on the fine-grained attention and global features we re-calculate the distance between the inter- and intra- classes, and we get better re-ranking results. Compared with state-of-the-art methods on three large-scale vehicle Re-ID datasets, our algorithm greatly improves the performance of vehicle Re-ID. [ABSTRACT FROM AUTHOR]

We explored the problem about function approximation error and complex mission adaptability in multi-agent deep reinforcement learning. This paper proposes a new multi-agent deep reinforcement learning algorithm framework named multi-agent time delayed deep deterministic policy gradient. Our work reduces the overestimation error of neural network approximation and variance of estimation result using dual-centered critic, group target network smoothing and delayed policy updating. According to experiment results, it improves the ability to adapt complex missions eventually. Then, we discuss that there is an inevitable overestimation issue about existing multi-agent algorithms about approximating real action-value equations with neural network. We also explain the approximate error of equations in the multi-agent deep deterministic policy gradient algorithm mathematically and experimentally. Finally, the application of our algorithm in the mixed cooperative competition experimental environment further demonstrates the effectiveness and generalization of our algorithm, especially improving the group's ability of adapting complex missions and completing more difficult missions. [ABSTRACT FROM AUTHOR]

To promote the combat capability of unmanned aerial vehicles (UAVs) in the future battlefield, the autonomous aerial refueling (AAR) technology becomes a challenging research issue. An accurate position relationship between the tanker and the receiver is significant for AAR. A novel drogue detection method is presented in this paper. The Adaptive boosting (Adaboost) and the convolutional neural networks (CNN) classifier with the improved focal loss (IFL) function are utilized to detect the drogue in complex environments. The sample imbalance during the training stage of the CNN classifier is solved by the IFL function. The PyTorch deep learning framework is employed to implement the software system with the graphics processing units (GPUs). Real scenario images with a mimetic drogue on the tanker are captured for training and testing dataset by the airborne camera on the receiver. The experimental results indicate that the presented algorithm can accelerate the detection speed and improve the detection accuracy. [ABSTRACT FROM AUTHOR]

One-shot learning has recently attracted growing attention to produce models which can classify significant events from a few or even no labeled examples. In this paper, we introduce a deep Q-network strategy into one-shot learning (OL-DQN) to design a more intelligent learner to infer whether to label a sample automatically or request the true label for the active-learning set-up. Then we conducted experiments in the ALOI dataset for the classification of objects recorded under various imaging circumstances and a dataset for handwriting recognition composed of both characters and digits to have a performance evaluation and application analysis of the proposed model respectively, and the obtained results demonstrate that our model can achieve a better trade-off between prediction accuracy and the need of label requests compared with a purely supervised task, a prior work AOL, and a conventional active learning algorithm QBC. [ABSTRACT FROM AUTHOR]

• Introduce the text detection models based on regression and segmentation according to their implementation methods. • Classify mainstream text recognition models and provide a detailed introduction. • Compare the performance of different text detection and recognition methods. • Discuss the future development trends of OCR. Optical Character Recognition (OCR) poses a crucial challenge within the realm of computer vision research, as it plays a pivotal role in converting vast amounts of unstructured text data into structured formats to support diverse artificial intelligence applications. The OCR process encompasses two core components: text detection and text recognition. Text detection involves identifying and extracting text regions, achieved through either object detection or segmentation techniques, while text recognition focuses on accurately deciphering the content within these identified regions. In recent years, remarkable strides have been made in the domain of text recognition, primarily driven by deep learning-based models. These models eliminate the need for manual feature processing and excel in recognizing text even within complex scenes, surpassing the performance of traditional text recognition methods and subsequently emerging as the dominant approach. The objective of this paper is to present a comprehensive survey of both text detection and text recognition models. Firstly, we systematically categorize and provide an overview of existing off-the-shelf text detection methods. Subsequently, we conduct an in-depth investigation of six distinct text recognition models, taking into account their unique implementations. Additionally, we explore and analyze the principal datasets that currently prevail in the field of text detection and recognition. Furthermore, this research entails a meticulous performance comparison of various text detection algorithms on the CTW1500, TotalText, and ICDAR2015 datasets. Additionally, we evaluate and scrutinize the efficacy of mainstream text recognition algorithms on the IIIT-5K, SVT, ICDAR2013, SVT-P, CUTE80, and ICDAR2015 datasets. Finally, we conclude with a discussion on the future development and research trends concerning text detection and recognition, providing insights that can further drive progress in this crucial area. [ABSTRACT FROM AUTHOR]

Abstract A Deep Boltzmann Machine is a model of a Deep Neural Network formed from multiple layers of neurons with nonlinear activation functions. The structure of a Deep Boltzmann Machine enables it to learn very complex relationships between features and facilitates advanced performance in learning of high-level representation of features, compared to conventional Artificial Neural Networks. Feature selection at the input level of Deep Neural Networks has not been well studied, despite its importance in reducing the input features processed by the deep learning model, which facilitates understanding of the data. This paper proposes a novel algorithm, Deep Feature Selection (Deep-FS), which is capable of removing irrelevant features from large datasets in order to reduce the number of inputs which are modelled during the learning process. The proposed Deep-FS algorithm utilizes a Deep Boltzmann Machine, and uses knowledge which is acquired during training to remove features at the beginning of the learning process. Reducing inputs is important because it prevents the network from learning the associations between the irrelevant features which negatively impact on the acquired knowledge of the network about the overall distribution of the data. The Deep-FS method embeds feature selection in a Restricted Boltzmann Machine which is used for training a Deep Boltzmann Machine. The generative property of the Restricted Boltzmann Machine is used to reconstruct eliminated features and calculate reconstructed errors, in order to evaluate the impact of eliminating features. The performance of the proposed approach was evaluated with experiments conducted using the MNIST, MIR-Flickr, GISETTE, MADELON and PANCAN datasets. The results revealed that the proposed Deep-FS method enables improved feature selection without loss of accuracy on the MIR-Flickr dataset, where Deep-FS reduced the number of input features by removing 775 features without reduction in performance. With regards to the MNIST dataset, Deep-FS reduced the number of input features by more than 45%; it reduced the network error from 0.97% to 0.90%, and also reduced processing and classification time by more than 5.5%. Additionally, when compared to classical feature selection methods, Deep-FS returned higher accuracy. The experimental results on GISETTE, MADELON and PANCAN showed that Deep-FS reduced 81%, 57% and 77% of the number of input features, respectively. Moreover, the proposed feature selection method reduced the classifier training time by 82%, 70% and 85% on GISETTE, MADELON and PANCAN datasets, respectively. Experiments with various datasets, comprising a large number of features and samples, revealed that the proposed Deep-FS algorithm overcomes the main limitations of classical feature selection algorithms. More specifically, most classical methods require, as a prerequisite, a pre-specified number of features to retain, however in Deep-FS this number is identified automatically. Deep-FS performs the feature selection task faster than classical feature selection algorithms which makes it suitable for deep learning tasks. In addition, Deep-FS is suitable for finding features in large and big datasets which are normally stored in data batches for faster and more efficient processing. [ABSTRACT FROM AUTHOR]

In this paper we propose and discuss different Deep Learning-based ensemble algorithms for a problem of low-visibility events prediction due to fog. Specifically, seven different Deep Learning (DL) architectures have been considered, from which multiple individual learners are generated. Hyperparameters of the models, including parameters concerning data preprocessing, models architecture and training procedure, are randomly selected for each model within a pre-defined discrete range. Also, every model is trained with slightly different data sampled randomly, assuring that every models introduce variety in the ensemble. Then, three different information fusion techniques are employed to build the ensemble models. The influence of the filtering process and the elitism level (the percentage of the individual models entering the ensemble) is also assessed. The performance of the proposed methodology have been tested in two real problems of low-visibility events prediction due to orographical and radiation fog, at the north of Spain. Comparison with different Machine Learning, alternative DL algorithms and meteorological-based methods show the good performance of the proposed deep learning ensembles in this problem. [ABSTRACT FROM AUTHOR]

There are two categories of partial shape matching problem: whole-to-part matching and part-to-part matching. The first establishes the best match between an open curve and a part of a closed curve, while the second is to find a part of the first input closed curve that can be well aligned with a part of the second input closed curve. In this paper, we present a novel approach to solve these two categories of the partial shape matching problem. First, we propose a novel shape descriptor, triangular centroid distances (TCDs), for shape representation; the TCDs shape descriptor is invariant to translation, rotation, scaling, and considerable shape deformations. Then, using the TCDs shape descriptor, we present a method to deal with the whole-to-part partial shape matching problem. Finally, we extend our work to part-to-part partial shape matching. Here, we propose a new approach, again using the TCDs shape descriptor, to solve the part-to-part partial shape matching problem. Experimental results demonstrate that our method outperforms existing methods in 2D nonrigid partial shape matching. [ABSTRACT FROM AUTHOR]

Word embeddings and CNN (convolutional neural networks) architecture are crucial ingredients of sentiment analysis. However, sentiment and lexicon embeddings are rarely used and CNN is incompetent to capture global features of sentence. To this end, semantic embeddings, sentiment embeddings and lexicon embeddings are applied for texts encoding, and three different attentions including attention vector, LSTM (long short term memory) attention and attentive pooling are integrated with CNN model in this paper. Additionally, a word and its context are explored to disambiguate the meaning of the word for rich input representation. To improve the performance of three different attention CNN models, CCR (cross-modality consistent regression) and transfer learning are presented. It is worth noticing that CCR and transfer learning are used in textual sentiment analysis for the first time. Finally, some experiments on two different datasets demonstrate that the proposed attention CNN models achieve the best or the next-best results against the existing state-of-the-art models. [ABSTRACT FROM AUTHOR]

This paper proposes a novel echo state network (ESN) architecture in a deep learning framework for time series prediction. The architecture is a uniform and consistent system with functional parts of the pre-training input network that effectively captures information with different degrees of abstraction in the observed data, and the minimum complexity ESN that possesses the powerful nonlinear approximation capability and highly efficient training. To our best knowledge, this is the first systematic model attempting to introduce the deep learning methodology to the ESN modeling, which provides a more robust alternative to the conventional shallow ESNs. Extensive experiments on various widely used benchmarks of different origins and features show that our model achieves a great enhancement in the prediction accuracy and short-term memory capacity, without significant tradeoff in the model’s computational efficiency. [ABSTRACT FROM AUTHOR]

Working up with deep learning techniques requires profound understanding of the mechanisms underlying the optimization of the internal parameters of complex structures. The major factor limiting this understanding is that there exist only a few optimization methods such as gradient descent and Limited–memory Broyden–Fletcher–Goldfarb–Shannon (L-BFGS) to find the best local minima of the problem space for these complex structures such as deep neural network (DNN). Therefore, in this paper, we represent a new training approach named hybrid artificial bee colony based training strategy (HABCbTS) to tune the parameters of a DNN structure, which includes one or more autoencoder layers cascaded to a softmax classification layer. In this strategy, a derivative-free optimization algorithm “ABC” is combined with a derivative-based algorithm “L-BFGS” to construct “HABC”, which is used in the HABCbTS. Detailed simulation results supported by statistical analysis show that the proposed training strategy results in better classification performance compared to the DNN classifier trained with the L-BFGS, ABC and modified ABC. The obtained classification results are also compared with the state-of-the-art classifiers, including MLP, SVM, KNN, DT and NB on 15 data sets with different dimensions and sizes. [ABSTRACT FROM AUTHOR]

Recently, a neighborhood based decision-theoretic rough set (NDTRS) model was proposed to deal with the general data which contained numerical values and noisy values simultaneously. However, it still suffered from the issue of granularity selection and the relationship between the thresholds and the neighborhood was also not investigated in depth. In this paper, a multi-objective optimization model for NDTRS to learn the thresholds and select the granularity (compute the neighborhood) comprehensively is proposed. In this model, three significant problems: decreasing the size of the boundary region, decreasing the overall decision cost for the three types of rules, and increasing the size of the neighborhood are taken into consideration. We use 10 UCI datasets to validate the performance of our method. With the Improved Strength Pareto Evolutionary Algorithm (SPEA2), the Pareto optimal solutions are obtained automatically. The experimental results demonstrate the trade-off among the three objectives and show that the thresholds and neighborhoods obtained by our method are more intuitive. [ABSTRACT FROM AUTHOR]

3D face reconstruction from a 2D face image has been found important to various applications such as face detection and recognition because a 3D face provides more semantic information than 2D image. This paper proposes a deep learning framework for 3D face reconstruction. The framework is designed to compute subspace feature of arbitrary face image, then map the feature to its counterpart in another subspace learned with 3D faces, and reconstruct the 3D face using the counterpart feature. During the course of training, we learn 2D and 3D subspaces through Stacked Contractive Autoencoders (SCAE), use a one-layer fully connected neural network to learn the mapping, and use the pre-trained parameters of the SCAEs and the one-layer network to initialize a deep feedforward neural network whose input are face images and output are 3D faces. The network is optimized by gradient descent algorithm with back-propagation. Extensive experimental results on various data sets indicate the effectiveness of the proposed SCAE-based 3D face reconstruction method. [ABSTRACT FROM AUTHOR]

Face representation is a crucial step of face detection system. In this paper, we present a fast face detection algorithm based on representation learnt using convolutional neural network (CNN) so as to explicitly capture various latent facial features. Firstly, in order to improve the speed of detection in the system, we train an Adaboost background filter which can remove the background most quickly. Secondly, we use the CNN to extract more distinctive features for those face and non-face patterns that have not been filtered by Adaboost. CNN can automatically learn and synthesize a problem-specific feature extractor from a training set, without making any assumptions or using any hand-made design concerning the features to extract or the areas of the face pattern to analyze. Finally, support vector machines (SVM) are used to detect instead of using the classification function of CNN itself. Extensive experiments demonstrate the robustness and efficiency of our system by comparing it with several popular face detection algorithms on the widely used CMU+MIT frontal face dataset and FDDB dataset. [ABSTRACT FROM AUTHOR]