Class Activation Mapping (CAM) has been widely adopted to generate saliency maps which provides visual explanations for deep neural networks (DNNs). The saliency maps are conventionally generated by fusing the channels of the target feature map using a weighted average scheme. It is a weak model for the inter-channel relation, in the sense that it only models the relation among channels in a contrastive way (i.e., channels that play key roles in the prediction are given higher weights for them to stand out in the fusion). The collaborative relation, which makes the channels work together to provide cross reference, has been ignored. Furthermore, the model has neglected the intra-channel relation thoroughly.In this paper, we address this problem by introducing Conceptor learning into CAM generation. Conceptor leaning has been originally proposed to model the patterns of state changes in recurrent neural networks (RNNs). By relaxing the dependency of Conceptor learning to RNNs, we make Conceptor-CAM not only generalizable to more DNN architectures but also able to learn both the inter- and intra-channel relations for better saliency map generation. Moreover, we have enabled the use of Boolean operations to combine the positive and pseudo-negative evidences, which has made the CAM inference more robust and comprehensive. The effectiveness of Conceptor-CAM has been validated with both formal verifications and experiments on the dataset of the largest scale in literature. The experimental results show that Conceptor-CAM is compatible with and can bring significant improvement to all well recognized CAM-based methods, and has outperformed the state-of-the-art methods by 43.14%~72.79% (88.39%~168.15%) on ILSVRC2012 in Average Increase (Drop), 15.42%~42.55% (47.09%~372.09%) on VOC, and 17.43%~31.32% (47.54%~206.45%) on COCO, respectively.
Fudan University（复旦大学）；Shanghai University of Finance and Economics（上海财经大学）；Deakin University（迪肯大学）
Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus on the most discriminative parts of an object (i.e., incomplete localization problem). In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background. To address it, we propose Class RE-Activation Mapping (CREAM), a novel clustering-based approach to…
Pohang University of Science and Technology（浦项科技大学）
This paper addresses the visualization task of deep learning models. To improve Class Activation Mapping (CAM) based visualization method, we offer two options. First, we propose Gaussian upsampling, an improved upsampling method that can reflect the characteristics of deep learning models. Second, we identify and modify unnatural terms in the mathematical derivation of the existing CAM studies. Based on two options, we propose Extended-CAM, an advanced CAM-based visualization method, which exhibits improved theoretical properties. Experimental results show that Extended-CAM provides more accu…
Xidian University（西安电子科技大学）；University of Montenegro（黑山大学）
Graph convolutional neural network (GCN) has drawn increasing attention and attained good performance in various computer vision tasks, however, there lacks a clear interpretation of GCN's inner mechanism. For standard convolutional neural networks (CNNs), class activation mapping (CAM) methods are commonly used to visualize the connection between CNN's decision and image region by generating a heatmap. Nonetheless, such heatmap usually exhibits semantic-chaos when these CAMs are applied to GCN directly. In this paper, we proposed a novel visualization method particularly applicable to GCN, Ve…
University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）
As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each input pixel with respect to the output of the network. In this paper, we focus on Class Activation Mapping (CAM) approaches, which provide an effective visualization by taking weighted averages of the activation maps. To enhance the evaluation and the reproducibility of such approaches, we propose a novel set of metrics to quantify explanation maps, which sh…
Increasing demands for understanding the internal behavior of convolutional neural networks (CNNs) have led to remarkable improvements in explanation methods. Particularly, several class activation mapping (CAM) based methods, which generate visual explanation maps by a linear combination of activation maps from CNNs, have been proposed. However, the majority of the methods lack a clear theoretical basis on how they assign the coefficients of the linear combination. In this paper, we revisit the intrinsic linearity of CAM with respect to the activation maps; we construct an explanation model o…
An open question in deep clustering is how to understand what in the image is creating the cluster assignments. This visual understanding is essential to be able to trust the results of an inherently complex algorithm like deep learning, especially when the derived cluster assignments may be used to inform decision-making or create new disease sub-types. In this work, we developed novel methodology to generate CLuster Activation Mapping (CLAM) which combines an unsupervised deep clustering framework with a modification of Score-CAM, an approach for discriminative localization in the supervised…
Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. However, class-insensitivity of the earlier layers in a network only allows saliency computation with low resolution activation maps of the deeper layers, resulting in compromised image saliency. Remedifying this can lead to sanity failures. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors and preserving the map sanity. Our method systematically performs multi-scale accumulation …
Deep neural networks (DNNs) have a high accuracy on image classification tasks. However, DNNs trained by such dataset with co-occurrence bias may rely on wrong features while making decisions for classification. It will greatly affect the transferability of pre-trained DNNs. In this paper, we propose an interactive method to direct classifiers paying attentions to the regions that are manually specified by the users, in order to mitigate the influence of co-occurrence bias. We test on CelebA dataset, the pre-trained AlexNet is fine-tuned to focus on the specific facial attributes based on the …
Fudan University（复旦大学）；Rensselaer Polytechnic Institute（伦斯勒理工学院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
A number of studies on lung nodule classification lack clinical/biological interpretations of the features extracted by convolutional neural network (CNN). The methods like class activation mapping (CAM) and gradient-based CAM (Grad-CAM) are tailored for interpreting localization and classification tasks while they ignored fine-grained features. Therefore, CAM and Grad-CAM cannot provide optimal interpretation for lung nodule categorization task in low-dose CT images, in that fine-grained pathological clues like discrete and irregular shape and margins of nodules are capable of enhancing sensi…
CF-CAM: Cluster Filter Class Activation Mapping for Reliable Gradient-Based Interpretability
School of Physics, Mathematics, and Computing（物理、数学与计算学院）；University of Western Australia（西澳大学）；Hefei University of Technology（合肥工业大学）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Stevens Institute of Technology（史蒂文斯理工学院）
Multi-view Feature Augmentation with Adaptive Class Activation Mapping
School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences（中国科学院虚拟经济与数据科学研究中心）；Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences（中国科学院大数据挖掘与知识管理重点实验室）
Max Planck Institute of Molecular Cell Biology and Genetics（马克斯·普朗克分子细胞生物学与遗传学研究所）；Center for Systems Biology Dresden（德累斯顿系统生物学中心）
Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been suggested for image classification, the interpretation of image segmentation still remains largely unexplored. To that end, we propose SEG-GRAD-CAM, a gradient-based method for interpreting semantic segmentation. Our method is an extension of the widely-used Grad-CAM method, applied locally to produce heatmaps showing the relevance of individual pixels for semantic…
Neural networks have shown to be a practical way of building a very complex mapping between a pre-specified input space and output space. For example, a convolutional neural network (CNN) mapping an image into one of a thousand object labels is approaching human performance in this particular task. However the mapping (neural network) does not automatically lend itself to other forms of queries, for example, to detect/reconstruct object instances, to enforce top-down signal on ambiguous inputs, or to recover object instances from occlusion. One way to address these queries is a backward pass t…
BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications
South China University of Technology（华南理工大学）；Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences)（广东省人民医院（广东省医学科学院））；Southern Medical University（南方医科大学）；The Chinese University of Hong Kong（香港中文大学）
The increased availability and accuracy of eye-gaze tracking technology has sparked attention-related research in psychology, neuroscience, and, more recently, computer vision and artificial intelligence. The attention mechanism in artificial neural networks is known to improve learning tasks. However, no previous research has combined the network attention and human attention. This paper describes a gaze-guided class activation mapping (GG-CAM) method to directly regulate the formation of network attention based on expert radiologists' visual attention for the chest X-ray pathology classifica…
Pests and diseases are relevant factors for production losses in agriculture and, therefore, promote a huge investment in the prevention and detection of its causative agents. In many countries, Integrated Pest Management is the most widely used process to prevent and mitigate the damages caused by pests and diseases in citrus crops. However, its results are credited by humans who visually inspect the orchards in order to identify the disease symptoms, insects and mite pests. In this context, we design a weakly supervised learning process guided by saliency maps to automatically select regions…
PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization
LIVIA, Dept. of Systems Engineering, ETS Montreal, Canada（LIVIA系统工程系，蒙特利尔大学ETS分校，加拿大）；Goodman Cancer Research Centre, Dept. of Oncology, McGill University, Montreal, Canada（Goodman癌症研究中心，麦吉尔大学肿瘤学系，加拿大）
Shandong University（山东大学）；Institute of Tsinghua-Berkeley Shenzhen, Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院清华-伯克利深圳学院）；Hangzhou Dianzi University（杭州电子科技大学）；Shenzhen ZNV Technology Co., Ltd（深圳中兴网信科技有限公司）；Shenzhen Graduate School of Harbin Institute of Technology（哈尔滨工业大学深圳研究生院）；Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院生物医药与健康工程研究院）
Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the localization and diagnosis of lesions. However, training these segmentation models requires a large number of manually annotated pixel-level labels, which are time-consuming and labor-intensive, in contrast to image-level labels that are easier to obtain. It is imperative to resolve this problem through weakly-supervised semantic segmentation models using image-…
Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions. In this paper, we develop a novel post-hoc visual explanation method called Score-CAM based on class activation mapping. Unlike previous class activation mapping based approaches, Score-CAM gets rid of the dependence on gradients by obtaining the weight of each activation map through its forward passing score on target class, the final result is obtained by a linear combination of weights and activation maps. We demonstrate that Sco…
Nagoya University（名古屋大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；National Institute of Informatics（国立信息学研究所）；Keio University School of Medicine（庆应义塾大学医学部）；Juntendo University（顺天堂大学）
This paper presents a fully-automated method for the identification of suspicious regions of a coronavirus disease (COVID-19) on chest CT volumes. One major role of chest CT scanning in COVID-19 diagnoses is identification of an inflammation particular to the disease. This task is generally performed by radiologists through an interpretation of the CT volumes, however, because of the heavy workload, an automatic analysis method using a computer is desired. Most computer-aided diagnosis studies have addressed only a portion of the elements necessary for the identification. In this work, we real…
CSEM SA（瑞士电子与微技术中心）；Swiss Federal Institute of Technology, ETH Zurich（苏黎世联邦理工学院）；University of Bologna（博洛尼亚大学）
While the accuracy of convolutional neural networks has achieved vast improvements by introducing larger and deeper network architectures, also the memory footprint for storing their parameters and activations has increased. This trend especially challenges power- and resource-limited accelerator designs, which are often restricted to store all network data in on-chip memory to avoid interfacing energy-hungry external memories. Maximizing the network size that fits on a given accelerator thus requires to maximize its memory utilization. While the traditionally used ping-pong buffering techniqu…
University of Oxford（牛津大学）；XRCE（施乐研究中心欧洲）；German Aerospace Center（德国航空航天中心）
Most saliency estimation methods aim to explicitly model low-level conspicuity cues such as edges or blobs and may additionally incorporate top-down cues using face or text detection. Data-driven methods for training saliency models using eye-fixation data are increasingly popular, particularly with the introduction of large-scale datasets and deep architectures. However, current methods in this latter paradigm use loss functions designed for classification or regression tasks whereas saliency estimation is evaluated on topographical maps. In this work, we introduce a new saliency map model wh…
Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. A series of ablation experiments support the importance of these identity mappings. This motivates us to propose a new residual unit, which makes training easier and impr…
Hubei University of Technology（湖北工业大学）；Central China Normal University（华中师范大学）
The black-box nature of Deep Neural Networks (DNNs) severely hinders its performance improvement and application in specific scenes. In recent years, class activation mapping-based method has been widely used to interpret the internal decisions of models in computer vision tasks. However, when this method uses backpropagation to obtain gradients, it will cause noise in the saliency map, and even locate features that are irrelevant to decisions. In this paper, we propose an Absolute value Class Activation Mapping-based (Abs-CAM) method, which optimizes the gradients derived from the backpropaga…
KU Leuven（鲁汶大学）；University of Antwerp（安特卫普大学）；imec-IDLab
One of the most common problems of weakly supervised object localization is that of inaccurate object coverage. In the context of state-of-the-art methods based on Class Activation Mapping, this is caused either by localization maps which focus, exclusively, on the most discriminative region of the objects of interest or by activations occurring in background regions. To address these two problems, we propose two representation regularization mechanisms: Full Region Regularizationwhich tries to maximize the coverage of the localization map inside the object region, and Common Region Regulariza…
Univ Lyon（里昂大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；ENS de Lyon（里昂高等师范学院）；Université Claude Bernard Lyon 1（里昂第一大学克洛德·贝尔纳大学）；Central European University（中欧大学）
Urbanisation is a great challenge for modern societies, promising better access to economic opportunities while widening socioeconomic inequalities. Accurately tracking how this process unfolds has been challenging for traditional data collection methods, while remote sensing information offers an alternative to gather a more complete view on these societal changes. By feeding a neural network with satellite images one may recover the socioeconomic information associated to that area, however these models lack to explain how visual features contained in a sample, trigger a given prediction. He…
University of Tübingen（蒂宾根大学）；Sogang University（西江大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；NAVER AI Lab（NAVER人工智能实验室）
The class activation mapping, or CAM, has been the cornerstone of feature attribution methods for multiple vision tasks. Its simplicity and effectiveness have led to wide applications in the explanation of visual predictions and weakly-supervised localization tasks. However, CAM has its own shortcomings. The computation of attribution maps relies on ad-hoc calibration steps that are not part of the training computational graph, making it difficult for us to understand the real meaning of the attribution values. In this paper, we improve CAM by explicitly incorporating a latent variable encodin…
Wroclaw University of Science and Technology（弗罗茨瓦夫理工大学）
In this paper, an enhancement technique for the class activation mapping methods such as gradient-weighted class activation maps or excitation backpropagation is proposed to present the visual explanations of decisions from convolutional neural network-based models. The proposed idea, called Gradual Extrapolation, can supplement any method that generates a heatmap picture by sharpening the output. Instead of producing a coarse localization map that highlights the important predictive regions in the image, the proposed method outputs the specific shape that most contributes to the model output.…
École de technologie supérieure（高等技术学院）；Ericsson（爱立信）；McGill University（麦吉尔大学）
Class Activation Mapping (CAM) methods have recently gained much attention for weakly-supervised object localization (WSOL) tasks. They allow for CNN visualization and interpretation without training on fully annotated image datasets. CAM methods are typically integrated within off-the-shelf CNN backbones, such as ResNet50. Due to convolution and pooling operations, these backbones yield low resolution CAMs with a down-scaling factor of up to 32, contributing to inaccurate localizations. Interpolation is required to restore full size CAMs, yet it does not consider the statistical properties of…
Weakly supervised video object localization (WSVOL) allows locating object in videos using only global video tags such as object class. State-of-art methods rely on multiple independent stages, where initial spatio-temporal proposals are generated using visual and motion cues, then prominent objects are identified and refined. Localization is done by solving an optimization problem over one or more videos, and video tags are typically used for video clustering. This requires a model per-video or per-class making for costly inference. Moreover, localized regions are not necessary discriminant b…
Benchmarking Class Activation Map Methods for Explainable Brain Hemorrhage Classification on Hemorica Dataset
Faculty of Computer Engineering, K. N. Toosi University of Technology（计算机工程学院，K.N.托菲大学）；Faculty of Electrical Engineering, K. N. Toosi University of Technology（电气工程学院，K.N.托菲大学）；Faculty of Mechanical Engineering, Tarbiat Modares University（机械工程学院，塔里比亚特莫达res大学）
