The interpretability of Convolutional Neural Networks (CNNs) is an important topic in the field of computer vision. In recent years, works in this field generally adopt a mature model to reveal the internal mechanism of CNNs, helping to understand CNNs thoroughly. In this paper, we argue the working mechanism of CNNs can be revealed through a totally different interpretation, by comparing the communication systems and CNNs. This paper successfully obtained the corresponding relationship between the modules of the two, and verified the rationality of the corresponding relationship with experiments. Finally, through the analysis of some cutting-edge research on neural networks, we find the inherent relation between these two tasks can be of help in explaining these researches reasonably, as well as helping us discover the correct research direction of neural networks.
Deep convolutional neural networks learn extremely powerful image representations, yet most of that power is hidden in the millions of deep-layer parameters. What exactly do these parameters represent? Recent work has started to analyse CNN representations, finding that, e.g., they are invariant to some 2D transformations Fischer et al. (2014), but are confused by particular types of image noise Nguyen et al. (2014). In this work, we delve deeper and ask: how invariant are CNNs to object-class variations caused by 3D shape, pose, and photorealism?
Tianjin University（天津大学）；Dalian University of Technology（大连理工大学）；Harbin Institute of Technology（哈尔滨工业大学）
Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task. Despite considerable advance, the reasons on effectiveness of GCP on deep CNNs have not been well studied. In this paper, we make an attempt to understand what deep CNNs benefit from GCP in a viewpoint of optimization. Specifically, we explore the effect of GCP on deep CNNs in terms of the Lipschitzness of optimization loss and the predictiveness of gradients, and show that GCP can make the optimization landscape …
Pennsylvania State University（宾夕法尼亚州立大学）；U. S. Naval Research Laboratory（美国海军研究实验室）
Finding mines in Sonar imagery is a significant problem with a great deal of relevance for seafaring military and commercial endeavors. Unfortunately, the lack of enormous Sonar image data sets has prevented automatic target recognition (ATR) algorithms from some of the same advances seen in other computer vision fields. Namely, the boom in convolutional neural nets (CNNs) which have been able to achieve incredible results - even surpassing human actors - has not been an easily feasible route for many practitioners of Sonar ATR. We demonstrate the power of one avenue to incorporating CNNs into…
Center for Research on Intelligent Perception and Computing（智能感知与计算研究中心）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Previous work has shown that feature maps of deep convolutional neural networks (CNNs) can be interpreted as feature representation of a particular image region. Features aggregated from these feature maps have been exploited for image retrieval tasks and achieved state-of-the-art performances in recent years. The key to the success of such methods is the feature representation. However, the different factors that impact the effectiveness of features are still not explored thoroughly. There are much less discussion about the best combination of them. The main contribution of our paper is the t…
University of Chinese Academy of Sciences（中国科学院大学）；Chinese Academy of Sciences（中国科学院）；Institute of Electronics, Chinese Academy of Sciences（中国科学院电子学研究所）
Deep convolutional neural networks (DCNNs) have attracted much attention in remote sensing recently. Compared with the large-scale annotated dataset in natural images, the lack of labeled data in remote sensing becomes an obstacle to train a deep network very well, especially in SAR image interpretation. Transfer learning provides an effective way to solve this problem by borrowing the knowledge from the source task to the target task. In optical remote sensing application, a prevalent mechanism is to fine-tune on an existing model pre-trained with a large-scale natural image dataset, such as …
On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process
Tokyo Denki University（东京电机大学）；Tokyo Institute of Technology（东京工业大学）；Tenchijin Inc.（天进公司）；National Institute of Advanced Industrial Science and Technology（国立先进工业技术研究所）
Tolerance to image variations (e.g. translation, scale, pose, illumination) is an important desired property of any object recognition system, be it human or machine. Moving towards increasingly bigger datasets has been trending in computer vision specially with the emergence of highly popular deep learning models. While being very useful for learning invariance to object inter- and intra-class shape variability, these large-scale wild datasets are not very useful for learning invariance to other parameters forcing researchers to resort to other tricks for training a model. In this work, we in…
A main issue preventing the use of Convolutional Neural Networks (CNN) in end user applications is the low level of transparency in the decision process. Previous work on CNN interpretability has mostly focused either on localizing the regions of the image that contribute to the result or on building an external model that generates plausible explanations. However, the former does not provide any semantic information and the latter does not guarantee the faithfulness of the explanation. We propose an intermediate representation composed of multiple Semantically Interpretable Activation Maps (S…
In this project, we adapt high-performing CNN architectures to differentiate between scenes with and without abandoned luggage. Using frames from two video datasets, we compare the results of training different architectures on each dataset as well as on combining the datasets. We additionally use network visualization techniques to gain insight into what the neural network sees, and the basis of the classification decision. We intend that our results benefit further work in applying CNNs in surveillance and security-related tasks.
While the research on convolutional neural networks (CNNs) is progressing quickly, the real-world deployment of these models is often limited by computing resources and memory constraints. In this paper, we address this issue by proposing a novel filter pruning method to compress and accelerate CNNs. Our work is based on the linear relationship identified in different feature map subspaces via visualization of feature maps. Such linear relationship implies that the information in CNNs is redundant. Our method eliminates the redundancy in convolutional filters by applying subspace clustering to…
Universitat Pompeu Fabra（庞培法布拉大学）；University of East Anglia（东英吉利大学）
Visual illusions teach us that what we see is not always what it is represented in the physical world. Its special nature make them a fascinating tool to test and validate any new vision model proposed. In general, current vision models are based on the concatenation of linear convolutions and non-linear operations. In this paper we get inspiration from the similarity of this structure with the operations present in Convolutional Neural Networks (CNNs). This motivated us to study if CNNs trained for low-level visual tasks are deceived by visual illusions. In particular, we show that CNNs train…
Convolutional neural networks (CNNs) were inspired by early findings in the study of biological vision. They have since become successful tools in computer vision and state-of-the-art models of both neural activity and behavior on visual tasks. This review highlights what, in the context of CNNs, it means to be a good model in computational neuroscience and the various ways models can provide insight. Specifically, it covers the origins of CNNs and the methods by which we validate them as models of biological vision. It then goes on to elaborate on what we can learn about biological vision by …
Wrocław University of Science and Technology（弗罗茨瓦夫理工大学）
Convolutional neural networks applied for real-world classification tasks need to recognize inputs that are far or out-of-distribution (OoD) with respect to the known or training data. To achieve this, many methods estimate class-conditional posterior probabilities and use confidence scores obtained from the posterior distributions. Recent works propose to use multivariate Gaussian distributions as models of posterior distributions at different layers of the CNN (i.e., for low- and upper-level features), which leads to the confidence scores based on the Mahalanobis distance. However, this proc…
Conventional neural network models (CNN), loosely inspired by the primate visual system, have been shown to predict neural responses in the visual cortex. However, the relationship between CNNs and the visual system is incomplete due to many reasons. On one hand state of the art CNN architecture is very complex, yet can be fooled by imperceptibly small, explicitly crafted perturbations which makes it hard difficult to map layers of the network with the visual system and to understand what they are doing. On the other hand, we don't know the exact mapping between feature space of the CNNs and t…
Ernst Strüngmann Institute for Neuroscience in Cooperation with Max Planck Society（与马克斯·普朗克学会合作的恩斯特·斯特伦格曼神经科学研究所）；Frankfurt Institute for Advanced Studies（法兰克福高等研究院）
Convolutional neural networks (CNNs) are one of the most successful computer vision systems to solve object recognition. Furthermore, CNNs have major applications in understanding the nature of visual representations in the human brain. Yet it remains poorly understood how CNNs actually make their decisions, what the nature of their internal representations is, and how their recognition strategies differ from humans. Specifically, there is a major debate about the question of whether CNNs primarily rely on surface regularities of objects, or whether they are capable of exploiting the spatial a…
Convolutional Neural Networks (CNNs) have made significant progress on several computer vision benchmarks, but are fraught with numerous non-human biases such as vulnerability to adversarial samples. Their lack of explainability makes identification and rectification of these biases difficult, and understanding their generalization behavior remains an open problem. In this work we explore the relationship between the generalization behavior of CNNs and the Singular Value Decomposition (SVD) of images. We show that naturally trained and adversarially robust CNNs exploit highly different feature…
VinAI Research（VinAI研究院）；University of Arkansas（阿肯色大学）
Medical image segmentation has been so far achieving promising results with Convolutional Neural Networks (CNNs). However, it is arguable that in traditional CNNs, its pooling layer tends to discard important information such as positions. Moreover, CNNs are sensitive to rotation and affine transformation. Capsule network is a data-efficient network design proposed to overcome such limitations by replacing pooling layers with dynamic routing and convolutional strides, which aims to preserve the part-whole relationships. Capsule network has shown a great performance in image recognition and nat…
Convolutional Neural Networks (CNNs) are state-of-the-art models for document image classification tasks. However, many of these approaches rely on parameters and architectures designed for classifying natural images, which differ from document images. We question whether this is appropriate and conduct a large empirical study to find what aspects of CNNs most affect performance on document images. Among other results, we exceed the state-of-the-art on the RVL-CDIP dataset by using shear transform data augmentation and an architecture designed for a larger input image. Additionally, we analyze…
Qualcomm AI Research（高通人工智能研究院）；Qualcomm Technologies Netherlands B.V.（高通科技荷兰有限公司）；EPFL（洛桑联邦理工学院）；U. of Amsterdam（阿姆斯特丹大学）
We present a general theory of Group equivariant Convolutional Neural Networks (G-CNNs) on homogeneous spaces such as Euclidean space and the sphere. Feature maps in these networks represent fields on a homogeneous base space, and layers are equivariant maps between spaces of fields. The theory enables a systematic classification of all existing G-CNNs in terms of their symmetry group, base space, and field type. We also consider a fundamental question: what is the most general kind of equivariant linear map between feature spaces (fields) of given types? Following Mackey, we show that such ma…
Romanian Institute of Science and Technology（罗马尼亚科学技术研究所）
Convolutional Neural Networks (CNNs) are build specifically for computer vision tasks for which it is known that the input data is a hierarchical structure based on locally correlated elements. The question that naturally arises is what happens with the performance of CNNs if one of the basic properties of the data is removed, e.g. what happens if the image pixels are randomly permuted? Intuitively one expects that the convolutional network performs poorly in these circumstances in contrast to a multilayer perceptron (MLPs) whose classification accuracy should not be affected by the pixel rand…
We study the effect of injecting local scale equivariance into Convolutional Neural Networks. This is done by applying each convolutional filter at multiple scales. The output is a vector field encoding for the maximally activating scale and the scale itself, which is further processed by the following convolutional layers. This allows all the intermediate representations to be locally scale equivariant. We show that this improves the performance of the model by over $20\%$ in the scale equivariant task of regressing the scaling factor applied to randomly scaled MNIST digits. Furthermore, we f…
Linköping University（林雪平大学）；University of Cambridge（剑桥大学）
Convolutional neural networks (CNNs) can model complicated non-linear relations between images. However, they are notoriously sensitive to small changes in the input. Most CNNs trained to describe image-to-image mappings generate temporally unstable results when applied to video sequences, leading to flickering artifacts and other inconsistencies over time. In order to use CNNs for video material, previous methods have relied on estimating dense frame-to-frame motion information (optical flow) in the training and/or the inference phase, or by exploring recurrent learning structures. We take a …
Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned representations is limited. In this work, we explore and employ the relationship between shape of kernels which define Receptive Fields (RFs) in CNNs for learning of feature representations and image classification. For this purpose, we first propose a feature visualization method for visualization of pixel-wise classification score maps of learned features. Motivated by our experimental results, and observations repo…
CNNs are often assumed to be capable of using contextual information about distinct objects (such as their directional relations) inside their receptive field. However, the nature and limits of this capacity has never been explored in full. We explore a specific type of relationship~-- directional~-- using a standard U-Net trained to optimize a cross-entropy loss function for segmentation. We train this network on a pretext segmentation task requiring directional relation reasoning for success and state that, with enough data and a sufficiently large receptive field, it succeeds to learn the p…
University College London（伦敦大学学院）；Kings College London（伦敦国王学院）
The performance of multi-task learning in Convolutional Neural Networks (CNNs) hinges on the design of feature sharing between tasks within the architecture. The number of possible sharing patterns are combinatorial in the depth of the network and the number of tasks, and thus hand-crafting an architecture, purely based on the human intuitions of task relationships can be time-consuming and suboptimal. In this paper, we present a probabilistic approach to learning task-specific and shared representations in CNNs for multi-task learning. Specifically, we propose "stochastic filter groups'' (SFG…
Convolutional Neural Networks (CNNs) are being increasingly used to address the problem of iris presentation attack detection. In this work, we propose attention-guided iris presentation attack detection (AG-PAD) to augment CNNs with attention mechanisms. Two types of attention modules are independently appended on top of the last convolutional layer of the backbone network. Specifically, the channel attention module is used to model the inter-channel relationship between features, while the position attention module is used to model inter-spatial relationship between features. An element-wise…
University of Central Florida（中佛罗里达大学）；Center for Research in Computer Vision（计算机视觉研究中心）
In this work, we explain in detail how receptive fields, effective receptive fields, and projective fields of neurons in different layers, convolution or pooling, of a Convolutional Neural Network (CNN) are calculated. While our focus here is on CNNs, the same operations, but in the reverse order, can be used to calculate these quantities for deconvolutional neural networks. These are important concepts, not only for better understanding and analyzing convolutional and deconvolutional networks, but also for optimizing their performance in real-world applications.
Pedestrian detection benefits greatly from deep convolutional neural networks (CNNs). However, it is inherently hard for CNNs to handle situations in the presence of occlusion and scale variation. In this paper, we propose W$^3$Net, which attempts to address above challenges by decomposing the pedestrian detection task into \textbf{\textit{W}}here, \textbf{\textit{W}}hat and \textbf{\textit{W}}hether problem directing against pedestrian localization, scale prediction and classification correspondingly. Specifically, for a pedestrian instance, we formulate its feature by three steps. i) We gene…
ZHAW Datalab & School of Engineering（苏黎世应用科技大学数据实验室与工程学院）；Institute of Neural Information Processing, Ulm University（乌尔姆大学神经信息处理研究所）
The existence of adversarial attacks on convolutional neural networks (CNN) questions the fitness of such models for serious applications. The attacks manipulate an input image such that misclassification is evoked while still looking normal to a human observer -- they are thus not easily detectable. In a different context, backpropagated activations of CNN hidden layers -- "feature responses" to a given input -- have been helpful to visualize for a human "debugger" what the CNN "looks at" while computing its output. In this work, we propose a novel detection method for adversarial examples to…
Ryerson University（瑞尔森大学）；Vector Institute for AI（矢量人工智能研究所）；Heidelberg University（海德堡大学）；University of Waterloo（滑铁卢大学）；University of Guelph（圭尔夫大学）；Samsung AI Centre Toronto（三星多伦多人工智能中心）
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a `texture bias': given an image with both texture and shape cues (e.g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture. However, these previous studies conduct experiments on the final classification output of the network, and fail to robustly evaluate the bias contained (i) in the latent representations, and (ii) on a per-pixel level. In this paper, we …
Convolutional Neural Networks (CNNs) have been successful in solving tasks in computer vision including medical image segmentation due to their ability to automatically extract features from unstructured data. However, CNNs are sensitive to rotation and affine transformation and their success relies on huge-scale labeled datasets capturing various input variations. This network paradigm has posed challenges at scale because acquiring annotated data for medical segmentation is expensive, and strict privacy regulations. Furthermore, visual representation learning with CNNs has its own flaws, e.g…
Hong Kong Baptist University（香港浸会大学）；Beijing Normal University（北京师范大学）
Convolutional neural networks (CNNs) show outstanding performance in many image processing problems, such as image recognition, object detection and image segmentation. Semantic segmentation is a very challenging task that requires recognizing, understanding what's in the image in pixel level. Though the state of the art has been greatly improved by CNNs, there is no explicit connections between prediction of neighbouring pixels. That is, spatial regularity of the segmented objects is still a problem for CNNs. In this paper, we propose a method to add spatial regularization to the segmented ob…
Microsoft Research（微软研究院）；University of California, Los Angeles（加州大学洛杉矶分校）
The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of what they have learned and how to further improve them. This paper investigates generative modeling of CNNs. The main contributions include: (1) We construct a generative model for the CNN in the form of exponential tilting of a reference distribution. (2) We propose a generative gradient for pre-training CNNs by a non-parametric importance sampling scheme, whi…
Residual networks are the current state of the art on ImageNet. Similar work in the direction of utilizing shortcut connections has been done extremely recently with derivatives of residual networks and with highway networks. This work potentially challenges our understanding that CNNs learn layers of local features that are followed by increasingly global features. Through qualitative visualization and empirical analysis, we explore the purpose that residual skip connections serve. Our assessments show that the residual shortcut connections force layers to refine features, as expected. We als…
In this survey paper, we review recent uses of convolution neural networks (CNNs) to solve inverse problems in imaging. It has recently become feasible to train deep CNNs on large databases of images, and they have shown outstanding performance on object classification and segmentation tasks. Motivated by these successes, researchers have begun to apply CNNs to the resolution of inverse problems such as denoising, deconvolution, super-resolution, and medical image reconstruction, and they have started to report improvements over state-of-the-art methods, including sparsity-based techniques suc…
In recent years, convolutional neural networks (CNNs) are used in a large number of tasks in computer vision. One of them is object detection for autonomous driving. Although CNNs are used widely in many areas, what happens inside the network is still unexplained on many levels. Our goal is to determine the effect of Intrinsic dimension (i.e. minimum number of parameters required to represent data) in different layers on the accuracy of object detection network for augmented data sets. Our investigation determines that there is difference between the representation of normal and augmented data…
Scattering Transforms (or ScatterNets) introduced by Mallat are a promising start into creating a well-defined feature extractor to use for pattern recognition and image classification tasks. They are of particular interest due to their architectural similarity to Convolutional Neural Networks (CNNs), while requiring no parameter learning and still performing very well (particularly in constrained classification tasks). In this paper we visualize what the deeper layers of a ScatterNet are sensitive to using a 'DeScatterNet'. We show that the higher orders of ScatterNets are sensitive to comple…
Ryerson University（瑞尔森大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）
In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent. An implication of this is that a filter may know what it is looking at, but not where it is positioned in the image. Information concerning absolute position is inherently useful, and it is reasonable to assume that deep CNNs may implicitly learn to encode this information if there is a means to do so. In this paper, we test this hypothesis revealing the surprising degree of absolute position information that is encoded…
Beijing University of Posts and Telecommunications（北京邮电大学）
Attention Mechanism is a widely used method for improving the performance of convolutional neural networks (CNNs) on computer vision tasks. Despite its pervasiveness, we have a poor understanding of what its effectiveness stems from. It is popularly believed that its effectiveness stems from the visual attention explanation, advocating focusing on the important part of input data rather than ingesting the entire input. In this paper, we find that there is only a weak consistency between the attention weights of features and their importance. Instead, we verify the crucial role of feature map m…
Center for Theoretical Neuroscience（理论神经科学中心）；Department of Neuroscience（神经科学系）；Columbia University（哥伦比亚大学）
Convolutional neural networks (CNNs) have proven effective for image processing tasks, such as object recognition and classification. Recently, CNNs have been enhanced with concepts of attention, similar to those found in biology. Much of this work on attention has focused on effective serial spatial processing. In this paper, I introduce a simple procedure for applying feature-based attention (FBA) to CNNs and compare multiple implementation options. FBA is a top-down signal applied globally to an input image which aides in detecting chosen objects in cluttered or noisy settings. The concept …
Image description generation plays an important role in many real-world applications, such as image retrieval, automatic navigation, and disabled people support. A well-developed task of image description generation is image captioning, which usually generates a short captioning sentence and thus neglects many of fine-grained properties, e.g., the information of subtle objects and their relationships. In this paper, we study the visual paragraph generation, which can describe the image with a long paragraph containing rich details. Previous research often generates the paragraph via a hierarch…
Norwegian University of Science and Technology（挪威科技大学）；University of Verona（维罗纳大学）；Sapienza Rome University（罗马第一大学）
Re-identification is generally carried out by encoding the appearance of a subject in terms of outfit, suggesting scenarios where people do not change their attire. In this paper we overcome this restriction, by proposing a framework based on a deep convolutional neural network, SOMAnet, that additionally models other discriminative aspects, namely, structural attributes of the human figure (e.g. height, obesity, gender). Our method is unique in many respects. First, SOMAnet is based on the Inception architecture, departing from the usual siamese framework. This spares expensive data preparati…
DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs
Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Nanyang Institute of Technology（南阳理工学院）；UNIUBI Research, Universal Ubiquitous Co.（普适智联（杭州）科技有限公司UNIUBI研究院）
Much of the recent progress in Vision-to-Language (V2L) problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. We propose here a method of incorporating high-level concepts into the very successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art performance in both image captioning and visual question answering. We also show that the same …
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；University College London（伦敦大学学院）
Image quality assessment (IQA) algorithm aims to quantify the human perception of image quality. Unfortunately, there is a performance drop when assessing the distortion images generated by generative adversarial network (GAN) with seemingly realistic texture. In this work, we conjecture that this maladaptation lies in the backbone of IQA models, where patch-level prediction methods use independent image patches as input to calculate their scores separately, but lack spatial relationship modeling among image patches. Therefore, we propose an Attention-based Hybrid Image Quality Assessment Netw…
Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape. How pervasive is this bias, and where does it come from? We find that, when trained on datasets of images with conflicting shape and texture, CNNs learn to classify by shape at least as easily as by texture. What factors, then, produce the texture bias in CNNs trained on ImageNet? Different unsupervised training objectives and different architectures have small but significant and largely independent effects on the level of texture bias. However, all objectives and arch…
