The gradient-weighted class activation mapping (Grad-CAM) method can faithfully highlight important regions in images for deep model prediction in image classification, image captioning and many other tasks. It uses the gradients in back-propagation as weights (grad-weights) to explain network decisions. However, applying Grad-CAM to embedding networks raises significant challenges because embedding networks are trained by millions of dynamically paired examples (e.g. triplets). To overcome these challenges, we propose an adaptation of the Grad-CAM method for embedding networks. First, we aggregate grad-weights from multiple training examples to improve the stability of Grad-CAM. Then, we develop an efficient weight-transfer method to explain decisions for any image without back-propagation. We extensively validate the method on the standard CUB200 dataset in which our method produces more accurate visual attention than the original Grad-CAM method. We also apply the method to a house price estimation application using images. The method produces convincing qualitative results, showcasing the practicality of our approach.
Adapting CNNs for Fisheye Cameras without Retraining
Australian Centre For Robotics (ACFR)（澳大利亚机器人中心）；School of Aerospace, Mechanical and Mechatronic Engineering（航空航天、机械与机电工程学院）；The University of Sydney（悉尼大学）
SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More
KOKONI, Moxin (Huzhou) Tech. Co., LTD（莫西（湖州）科技有限公司KOKONI）；Beihang University（北京航空航天大学）；Zhejiang University（浙江大学）；Huzhou University（湖州师范学院）；Singapore University of Technology and Design（新加坡科技设计大学）
Computer vision tasks often have side information available that is helpful to solve the task. For example, for crowd counting, the camera perspective (e.g., camera angle and height) gives a clue about the appearance and scale of people in the scene. While side information has been shown to be useful for counting systems using traditional hand-crafted features, it has not been fully utilized in counting systems based on deep learning. In order to incorporate the available side information, we propose an adaptive convolutional neural network (ACNN), where the convolutional filter weights adapt …
SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More
KOKONI, Moxin (Huzhou) Tech. Co., LTD（科科尼（湖州）魔芯科技有限公司）；School of Information Engineering, Huzhou University（湖州大学信息工程学院）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）；School of Software Technology, Zhejiang University（浙江大学软件学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Information Systems Technology and Design Pillar, Singapore University of Technology and Design（新加坡科技设计大学信息系统技术与设计支柱学院）
Monitoring and Adapting the Physical State of a Camera for Autonomous Vehicles
German Aerospace Center (DLR)（德国航空航天中心）；TU Berlin（柏林工业大学）；Einstein Center Digital Future（爱因斯坦数字未来中心）；Science of Intelligence Excellence Cluster（科学智能卓越集群）
Power consumption is a critical factor for the deployment of embedded computer vision systems. We explore the use of computational cameras that directly output binary gradient images to reduce the portion of the power consumption allocated to image sensing. We survey the accuracy of binary gradient cameras on a number of computer vision tasks using deep learning. These include object recognition, head pose regression, face detection, and gesture recognition. We show that, for certain applications, accuracy can be on par or even better than what can be achieved on traditional images. We are als…
Gaining insight into how deep convolutional neural network models perform image classification and how to explain their outputs have been a concern to computer vision researchers and decision makers. These deep models are often referred to as black box due to low comprehension of their internal workings. As an effort to developing explainable deep learning models, several methods have been proposed such as finding gradients of class output with respect to input image (sensitivity maps), class activation map (CAM), and Gradient based Class Activation Maps (Grad-CAM). These methods under perform…
FiveAI Ltd.（FiveAI有限公司）；University of Oxford（牛津大学）
Many applications require a camera to be relocalised online, without expensive offline training on the target scene. Whilst both keyframe and sparse keypoint matching methods can be used online, the former often fail away from the training trajectory, and the latter can struggle in textureless regions. By contrast, scene coordinate regression (SCoRe) methods generalise to novel poses and can leverage dense correspondences to improve robustness, and recent work has shown how to adapt SCoRe forests between scenes, allowing their state-of-the-art performance to be leveraged online. However, becau…
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. However, the average gradient-based terms deployed in this method underestimates the contribution of the representations discovered by the model to its predictions. Addressing this problem, we introduce a solution to tackle this issue by computing the path integral of t…
In this paper, we run two methods of explanation, namely LIME and Grad-CAM, on a convolutional neural network trained to label images with the LEGO bricks that are visible in them. We evaluate them on two criteria, the improvement of the network's core performance and the trust they are able to generate for users of the system. We find that in general, Grad-CAM seems to outperform LIME on this specific task: it yields more detailed insight from the point of view of core performance and 80\% of respondents asked to choose between them when it comes to the trust they inspire in the model choose …
The Grad-CAM algorithm provides a way to identify what parts of an image contribute most to the output of a classifier deep network. The algorithm is simple and widely used for localization of objects in an image, although some researchers have point out its limitations, and proposed various alternatives. One of them is Grad-CAM++, that according to its authors can provide better visual explanations for network predictions, and does a better job at locating objects even for occurrences of multiple object instances in a single image. Here we show that Grad-CAM++ is practically equivalent to a v…
Seoul National University（首尔国立大学）；Seoul National University Hospital（首尔国立大学医院）
A meningioma is a type of brain tumor that requires tumor volume size follow ups in order to reach appropriate clinical decisions. A fully automated tool for meningioma detection is necessary for reliable and consistent tumor surveillance. There have been various studies concerning automated lesion detection. Studies on the application of convolutional neural network (CNN)-based methods, which have achieved a state-of-the-art level of performance in various computer vision tasks, have been carried out. However, the applicable diseases are limited, owing to a lack of strongly annotated data bei…
Pohang University of Science and Technology (POSTECH)（浦项科技大学）
Consistency training, which exploits both supervised and unsupervised learning with different augmentations on image, is an effective method of utilizing unlabeled data in semi-supervised learning (SSL) manner. Here, we present another version of the method with Grad-CAM consistency loss, so it can be utilized in training model with better generalization and adjustability. We show that our method improved the baseline ResNet model with at most 1.44 % and 0.31 $\pm$ 0.59 %p accuracy improvement on average with CIFAR-10 dataset. We conducted ablation study comparing to using only psuedo-label fo…
Fine-grained visual classification (FGVC) is becoming an important research field, due to its wide applications and the rapid development of computer vision technologies. The current state-of-the-art (SOTA) methods in the FGVC usually employ attention mechanisms to first capture the semantic parts and then discover their subtle differences between distinct classes. The channel-spatial attention mechanisms, which focus on the discriminative channels and regions simultaneously, have significantly improved the classification performance. However, the existing attention modules are poorly guided s…
We present Smooth Grad-CAM++, a technique which combines two recent techniques: SMOOTHGRAD and Grad-CAM++. Smooth Grad-CAM++ has the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map at each instance. We experimented with few images, and we discovered that Smooth Grad-CAM++ produced more visually sharp maps with larger number of salient pixels highlighted in the given input images when compared with other methods. Smooth Grad-CAM++ will give insight into what our deep CNN models (including models trained on medical scan or imagery) lear…
University of Sydney（悉尼大学）；The Chinese University of Hong Kong（香港中文大学）；Sensetime Group Limited（商汤集团有限公司）
Human beings can quickly adapt to environmental changes by leveraging learning experience. However, adapting deep neural networks to dynamic environments by machine learning algorithms remains a challenge. To better understand this issue, we study the problem of continual domain adaptation, where the model is presented with a labelled source domain and a sequence of unlabelled target domains. The obstacles in this problem are both domain shift and catastrophic forgetting. We propose Gradient Regularized Contrastive Learning (GRCL) to solve the obstacles. At the core of our method, gradient reg…
The Convolutional Neural Network (CNN) is a widely used deep learning architecture for computer vision. However, its black box nature makes it difficult to interpret the behavior of the model. To mitigate this issue, AI practitioners have explored explainable AI methods like Class Activation Map (CAM) and Grad-CAM. Although these methods have shown promise, they are limited by architectural constraints or the burden of gradient computing. To overcome this issue, Score-CAM and Ablation-CAM have been proposed as gradient-free methods, but they have longer execution times compared to CAM or Grad-…
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）；Cisco Systems（思科系统公司）
Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems. However, these deep models are perceived as "black box" methods considering the lack of understanding of their internal functioning. There has been a significant recent interest in developing explainable deep learning models, and this paper is an effort in this direction. Building on a recently proposed method called Grad-CAM, we propose a generalized method called Grad-CAM++ that can provide better visual explanations of CNN model predictions, in terms of better obje…
Yale University（耶鲁大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Central Florida（中佛罗里达大学）
Most popular optimizers for deep learning can be broadly categorized as adaptive methods (e.g. Adam) and accelerated schemes (e.g. stochastic gradient descent (SGD) with momentum). For many models such as convolutional neural networks (CNNs), adaptive methods typically converge faster but generalize worse compared to SGD; for complex settings such as generative adversarial networks (GANs), adaptive methods are typically the default because of their stability.We propose AdaBelief to simultaneously achieve three goals: fast convergence as in adaptive methods, good generalization as in SGD, and t…
Adobe Research（奥多比研究院）；KAIST（韩国科学技术院）；Hyundai Motor Group（现代汽车集团）
We introduce a novel method to automatically adjust camera exposure for image processing and computer vision applications on mobile robot platforms. Because most image processing algorithms rely heavily on low-level image features that are based mainly on local gradient information, we consider that gradient quantity can determine the proper exposure level, allowing a camera to capture the important image features in a manner robust to illumination conditions. We then extend this concept to a multi-camera system and present a new control algorithm to achieve both brightness consistency between…
California Institute of Technology（加州理工学院）；Kitware（Kitware公司）；Rensselaer Polytechnic Institute（伦斯勒理工学院）；Wild Me；Conservation X Labs；Mpala Research Centre（姆帕拉研究中心）；Ohio State University（俄亥俄州立大学）；Princeton University（普林斯顿大学）；Massachusetts Institute of Technology（麻省理工学院）
We consider a light-weight method which allows to improve the explainability of localized classification networks. The method considers (Grad)CAM maps during the training process by modification of the training loss and does not require additional structural elements. It is demonstrated that the (Grad)CAM interpretability, as measured by several indicators, can be improved in this way. Since the method shall be applicable on embedded systems and on standard deeper architectures, it essentially takes advantage of second order derivatives during the training and does not require additional model…
Xidian University（西安电子科技大学）；University of Montenegro（黑山大学）
Despite the tremendous success of convolutional neural networks (CNNs) in computer vision, the mechanism of CNNs still lacks clear interpretation. Currently, class activation mapping (CAM), a famous visualization technique to interpret CNN's decision, has drawn increasing attention. Gradient-based CAMs are efficient while the performance is heavily affected by gradient vanishing and exploding. In contrast, gradient-free CAMs can avoid computing gradients to produce more understandable results. However, existing gradient-free CAMs are quite time-consuming because hundreds of forward interferenc…
St. Pölten University of Applied Sciences（圣珀尔滕应用科学大学）；EYYES GmbH（EYYES有限公司）
We investigate the problem of explainability for visual object detectors. Specifically, we demonstrate on the example of the YOLO object detector how to integrate Grad-CAM into the model architecture and analyze the results. We show how to compute attribution-based explanations for individual detections and find that the normalization of the results has a great impact on their interpretation.
Gradient-weighted Class Activation Mapping (Grad- CAM), is an example-based explanation method that provides a gradient activation heat map as an explanation for Convolution Neural Network (CNN) models. The drawback of this method is that it cannot be used to generalize CNN behaviour. In this paper, we present a novel method that extends Grad-CAM from example-based explanations to a method for explaining global model behaviour. This is achieved by introducing two new metrics, (i) Mean Observed Dissimilarity (MOD) and (ii) Variation in Dissimilarity (VID), for model generalization. These metric…
Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human guidance. The performance of CAM-like studies depends on the governing model's layer response, and the influences of the gradients. Typical gradient-oriented CAM studies rely on weighted aggregation for saliency map estimation by projecting the gradient maps into single weight values, which may lead to over generalized saliency map. To address this issue, we …
Dipartimento di Fisica, Politecnico di Torino（都灵理工大学物理系）
Instead of evaluating the gradient field of the brightness map of an image, we propose the use of dipole vectors. This approach is obtained by adapting to the image gray-tone distribution the definition of the dipole moment of charge distributions. We will show how to evaluate the dipoles and obtain a vector field, which can be a good alternative to the gradient field in pattern recognition.
AIST（产业技术综合研究所）；Tokyo Institute of Technology（东京工业大学）；NEC Corporation（日本电气股份有限公司）
A low-light image enhancement is a highly demanded image processing technique, especially for consumer digital cameras and cameras on mobile phones. In this paper, a gradient-based low-light image enhancement algorithm is proposed. The key is to enhance the gradients of dark region, because the gradients are more sensitive for human visual system than absolute values. In addition, we involve the intensity-range constraints for the image integration. By using the intensity-range constraints, we can integrate the output image with enhanced gradients preserving the given gradient information whil…
To have a better understanding and usage of Convolution Neural Networks (CNNs), the visualization and interpretation of CNNs has attracted increasing attention in recent years. In particular, several Class Activation Mapping (CAM) methods have been proposed to discover the connection between CNN's decision and image regions. In spite of the reasonable visualization, lack of clear and sufficient theoretical support is the main limitation of these methods. In this paper, we introduce two axioms -- Conservation and Sensitivity -- to the visualization paradigm of the CAM methods. Meanwhile, a dedi…
Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations. We illustrate a previously unrecognized limitation of the popular neural network explanation method Grad-CAM: as a side effect of the gradient averaging step, Grad-CAM sometimes highlights locations the model did not actually use. To solve this problem, we propose HiResCAM, a novel class-specific explanation method that is guaranteed to highlight only the locations the model used to make each prediction. We prove that HiResCAM is a generalization of CAM and explor…
University of Central Florida（中佛罗里达大学）；Amazon Web Services（亚马逊云科技）
Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally expensive and unnecessary, given the pre-trained image transformer models have demonstrated exceptional transferability. In this work, we propose a novel method to Adapt pre-trained Image Models (AIM) for efficient video understanding. By freezing the pre-trained image model and adding a few lightweight Adapters, we introduce spatial adaptation, temporal ad…
Georgia Institute of Technology（佐治亚理工学院）；Facebook AI Research（Facebook人工智能研究院）
We propose a technique for producing "visual explanations" for decisions from a large class of CNN-based models, making them more transparent. Our approach - Gradient-weighted Class Activation Mapping (Grad-CAM), uses the gradients of any target concept, flowing into the final convolutional layer to produce a coarse localization map highlighting important regions in the image for predicting the concept. Grad-CAM is applicable to a wide variety of CNN model-families: (1) CNNs with fully-connected layers, (2) CNNs used for structured outputs, (3) CNNs used in tasks with multimodal inputs or rein…
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）
We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class Activation Mapping (Grad-CAM), uses class-specific gradient information to localize important regions. These localizations are combined with existing pixel-space visualizations to create a novel high-resolution and class-discriminative visualization called Guided Grad-CAM. These methods help better understand CNN-based models, including image captioning and vis…
Technical university of Darmstadt（达姆施塔特工业大学）；Universitätsklinikum Frankfurt（法兰克福大学医院）
M3d-CAM is an easy to use library for generating attention maps of CNN-based PyTorch models improving the interpretability of model predictions for humans. The attention maps can be generated with multiple methods like Guided Backpropagation, Grad-CAM, Guided Grad-CAM and Grad-CAM++. These attention maps visualize the regions in the input data that influenced the model prediction the most at a certain layer. Furthermore, M3d-CAM supports 2D and 3D data for the task of classification as well as for segmentation. A key feature is also that in most cases only a single line of code is required for…
RISE Research Institutes of Sweden（瑞典RISE研究所）；Lund University（隆德大学）
Machine Learning (ML) is a fundamental part of modern perception systems. In the last decade, the performance of computer vision using trained deep neural networks has outperformed previous approaches based on careful feature engineering. However, the opaqueness of large ML models is a substantial impediment for critical applications such as in the automotive context. As a remedy, Gradient-weighted Class Activation Mapping (Grad-CAM) has been proposed to provide visual explanations of model internals. In this paper, we demonstrate how Grad-CAM heatmaps can be used to increase the explainabilit…
Institute of Theoretical Physics（理论物理研究所）；Faculty of Mathematics and Computer Science（数学与计算机科学学院）；Jagiellonian University（雅盖隆大学）
We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a standard gradient-based training. The resulting network has the structure of a graph tailored to the particular learning task and dataset. The obtained networks can also be trained from scratch and achieve virtually identical performance. We explore the properties of the network architectures for a number of datasets of varying difficulty observing systematic regularities. The obtained graphs can be therefore understood as encoding nontrivial characteristics of the particular …
The Resilient Propagation (Rprop) algorithm has been very popular for backpropagation training of multilayer feed-forward neural networks in various applications. The standard Rprop however encounters difficulties in the context of deep neural networks as typically happens with gradient-based learning algorithms. In this paper, we propose a modification of the Rprop that combines standard Rprop steps with a special drop out technique. We apply the method for training Deep Neural Networks as standalone components and in ensemble formulations. Results on the MNIST dataset show that the proposed …
