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 when localizing multiple occurrences of the same class and do not work for all CNNs. In addition, Grad-CAM does not capture the entire object in completeness when used on single object images, this affect performance on recognition tasks. With the intention to create an enhanced visual explanation in terms of visual sharpness, object localization and explaining multiple occurrences of objects in a single image, we present Smooth Grad-CAM++ \footnote{Simple demo: http://35.238.22.135:5000/}, a technique that combines methods from two other recent techniques---SMOOTHGRAD and Grad-CAM++. Our Smooth Grad-CAM++ technique provides the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map at each instance at the inference level (model prediction process). After experimenting with few images, Smooth Grad-CAM++ produced more visually sharp maps with better localization of objects in the given input images when compared with other methods.
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…
University of Florence（佛罗伦萨大学）；Columbia University（哥伦比亚大学）
In this paper we present a machine vision system to efficiently monitor, analyze and present visual data acquired with a railway overhead gantry equipped with multiple cameras. This solution aims to improve the safety of daily life railway transportation in a two- fold manner: (1) by providing automatic algorithms that can process large imagery of trains (2) by helping train operators to keep attention on any possible malfunction. The system is designed with the latest cutting edge, high-rate visible and thermal cameras that ob- serve a train passing under an railway overhead gantry. The machi…
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…
The convolutional neural network (CNN) has become a powerful tool for various biomedical image analysis tasks, but there is a lack of visual explanation for the machinery of CNNs. In this paper, we present a novel algorithm, Respond-weighted Class Activation Mapping (Respond-CAM), for making CNN-based models interpretable by visualizing input regions that are important for predictions, especially for biomedical 3D imaging data inputs. Our method uses the gradients of any target concept (e.g. the score of target class) that flows into a convolutional layer. The weighted feature maps are combine…
Computer Vision Lab Delft University of Technology（代尔夫特理工大学计算机视觉实验室）；Delft University of Technology（代尔夫特理工大学）；The Netherlands（荷兰（注：原文本中The Netherlands为国家名，根据提取规则，国家不属于机构，此处仅为完整显示原机构相关信息））；Computer Vision Lab（计算机视觉实验室）
Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visualization methods, including class activation mapping (CAM) and Grad-CAM, use only the deepest, lowest resolution convolutional layer, missing all information in intermediate layers. We propose Zoom-CAM: going beyond the last lowest resolution layer by integrating the importance maps over all activations in intermediate layers. Zoom-CAM captures fine-grained small-scale objects for various discriminative class instance…
This document summarizes different visual explanations methods such as CAM, Grad-CAM, Localization using Multiple Instance Learning - Saliency-based methods, Saliency-driven Class-Impressions, Muting pixels in input image - Adversarial methods and Activation visualization, Convolution filter visualization - Feature-based methods. We have also shown the results produced by different methods and a comparison between CAM, GradCAM, and Guided Backpropagation.
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…
We explain theoretically how to reconstruct the 3D scene from successive frames in order to see the video in 3D. To do this, features, associated to moving rigid objects in 3D, are extracted in frames and matched. The vanishing point computed in frame corresponding to the direction of moving object is used for 3D positioning of the 3D structure of the moving object. First experiments are conducted and the obtained results are shown and publicly available. They demonstrate the feasibility of our method. We conclude this paper by future works in order to improve this method tacking into account …
Automatic analysis of the enormous sets of images is a critical task in life sciences. This faces many challenges such as: algorithms are highly parameterized, significant human input is intertwined, and lacking a standard meta-visualization approach. This paper proposes an alternative iterative approach for optimizing input parameters, saving time by minimizing the user involvement, and allowing for understanding the workflow of algorithms and discovering new ones. The main focus is on developing an interactive visualization technique that enables users to analyze the relationships between sa…
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 aggr…
Retrieval networks are essential for searching and indexing. Compared to classification networks, attention visualization for retrieval networks is hardly studied. We formulate attention visualization as a constrained optimization problem. We leverage the unit L2-Norm constraint as an attention filter (L2-CAF) to localize attention in both classification and retrieval networks. Unlike recent literature, our approach requires neither architectural changes nor fine-tuning. Thus, a pre-trained network's performance is never undermined L2-CAF is quantitatively evaluated using weakly supervised obj…
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…
A panoramic image mosaic is an attractive visualization for viewing many overlapping photos, but its images must be both captured and processed correctly to produce an acceptable composite. We propose Swipe Mosaics, an interactive visualization that places the individual video frames on a 2D planar map that represents the layout of the physical scene. Compared to traditional panoramic mosaics, our capture is easier because the user can both translate the camera center and film moving subjects. Processing and display degrade gracefully if the footage lacks distinct, overlapping, non-repeating t…
The School of Computer Science, Tel Aviv University（特拉维夫大学计算机科学学院）
Neural network visualization techniques mark image locations by their relevancy to the network's classification. Existing methods are effective in highlighting the regions that affect the resulting classification the most. However, as we show, these methods are limited in their ability to identify the support for alternative classifications, an effect we name {\em the saliency bias} hypothesis. In this work, we integrate two lines of research: gradient-based methods and attribution-based methods, and develop an algorithm that provides per-class explainability. The algorithm back-projects the p…
The internal states of most deep neural networks are difficult to interpret, which makes diagnosis and debugging during training challenging. Activation maximization methods are widely used, but lead to multiple optima and are hard to interpret (appear noise-like) for complex neurons. Image-based methods use maximally-activating image regions which are easier to interpret, but do not provide pixel-level insight into why the neuron responds to them. In this work we introduce an MCMC method: Langevin Dynamics Activation Maximization (LDAM), which is designed for diagnostic visualization. LDAM pr…
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…
Synthetic Aperture Radar (SAR) imagery has diverse applications in land and marine surveillance. Unlike electro-optical (EO) systems, these systems are not affected by weather conditions and can be used in the day and night times. With the growing importance of SAR imagery, it would be desirable if models trained on widely available EO datasets can also be used for SAR images. In this work, we consider transfer learning to leverage deep features from a network trained on an EO ships dataset and generate predictions on SAR imagery. Furthermore, by exploring the network activations in the form o…
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 …
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…
Technische Universität München（慕尼黑工业大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Medical Mixed Reality helps surgeons to contextualize intraoperative data with video of the surgical scene. Nonetheless, the surgical scene and anatomical target are often occluded by surgical instruments and surgeon hands. In this paper and to our knowledge, we propose a multi-layer visualization in Medical Mixed Reality solution which subtly improves a surgeon's visualization by making transparent the occluding objects. As an example scenario, we use an augmented reality C-arm fluoroscope device. A video image is created using a volumetric-based image synthesization technique and stereo-RGBD…
In this article, we describe and validate the first fully automatic parameter optimization for thermal synthetic aperture visualization. It replaces previous manual exploration of the parameter space, which is time consuming and error prone. We prove that the visibility of targets in thermal integral images is proportional to the variance of the targets' image. Since this is invariant to occlusion it represents a suitable objective function for optimization. Our findings have the potential to enable fully autonomous search and recuse operations with camera drones.
Idiap Research Institute（Idiap 研究所）；EPFL（洛桑联邦理工学院）
We introduce a new tool for interpreting neural net responses, namely full-gradients, which decomposes the neural net response into input sensitivity and per-neuron sensitivity components. This is the first proposed representation which satisfies two key properties: completeness and weak dependence, which provably cannot be satisfied by any saliency map-based interpretability method. For convolutional nets, we also propose an approximate saliency map representation, called FullGrad, obtained by aggregating the full-gradient components. We experimentally evaluate the usefulness of FullGrad in e…
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…
University of Waterloo（滑铁卢大学）；Ludwig-Maximilians University（路德维希-马克西米利安大学）；Technical University of Munich（慕尼黑工业大学）；Schön Klinik München Schwabing（慕尼黑施瓦宾 Schön 诊所）
Parkinson's Disease (PD) is characterized by disorders in motor function such as freezing of gait, rest tremor, rigidity, and slowed and hyposcaled movements. Medication with dopaminergic medication may alleviate those motor symptoms, however, side-effects may include uncontrolled movements, known as dyskinesia. In this paper, an automatic PD motor-state assessment in free-living conditions is proposed using an accelerometer in a wrist-worn wearable sensor. In particular, an ensemble of convolutional neural networks (CNNs) is applied to capture the large variability of daily-living activities …
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…
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…
Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single im…
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…
Understanding how cities visually differ from each others is interesting for planners, residents, and historians. We investigate the interpretation of deep features learned by convolutional neural networks (CNNs) for city recognition. Given a trained city recognition network, we first generate weighted masks using the known Grad-CAM technique and to select the most discriminate regions in the image. Since the image classification label is the city name, it contains no information of objects that are class-discriminate, we investigate the interpretability of deep representations with two method…
Manipulating Feature Visualizations with Gradient Slingshots
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；UMI Lab, ATB Potsdam（UMI实验室，ATB波茨坦）；University of Potsdam（波茨坦大学）；BIFOLD（BIFOLD机构）；Machine Learning and Security Group, TU Berlin（柏林技术大学机器学习与安全小组）；Machine Learning Group, TU Berlin（柏林技术大学机器学习小组）；Department of Artificial Intelligence, Korea University（韩国大学人工智能系）；Max-Planck Institute for Informatics（马克斯·普朗克信息研究所）；Centre of eXplainable Artificial Intelligence, TU Dublin（都柏林技术大学可解释人工智能中心）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））；TU Munich（慕尼黑技术大学）
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.…
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…
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-…
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…
Weakly-supervised object detection has recently attracted increasing attention since it only requires image-levelannotations. However, the performance obtained by existingmethods is still far from being satisfactory compared with fully-supervised object detection methods. To achieve a good trade-off between annotation cost and object detection performance,we propose a simple yet effective method which incorporatesCNN visualization with click supervision to generate the pseudoground-truths (i.e., bounding boxes). These pseudo ground-truthscan be used to train a fully-supervised detector. To est…
Hunan University（湖南大学）；State University of New York at New Paltz（纽约州立大学新帕尔茨分校）
Recent researches introduced fast, compact and efficient convolutional neural networks (CNNs) for offline handwritten Chinese character recognition (HCCR). However, many of them did not address the problem of network interpretability. We propose a new architecture of a deep CNN with high recognition performance which is capable of learning deep features for visualization. A special characteristic of our model is the bottleneck layers which enable us to retain its expressiveness while reducing the number of multiply-accumulate operations and the required storage. We introduce a modification of …
Federal Office of Meteorology and Climatology MeteoSwiss（瑞士联邦气象与气候办公室）；Comerge（Comerge公司）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；ETH Zürich（苏黎世联邦理工学院）；University of Amsterdam（阿姆斯特丹大学）
Outdoor webcam images are an information-dense yet accessible visualization of past and present weather conditions, and are consulted by meteorologists and the general public alike. Weather forecasts, however, are still communicated as text, pictograms or charts. We therefore introduce a novel method that uses photographic images to also visualize future weather conditions. This is challenging, because photographic visualizations of weather forecasts should look real, be free of obvious artifacts, and should match the predicted weather conditions. The transition from observation to forecast sh…
Charles Sturt University（查尔斯特大学）；University of Western Sydney（西悉尼大学）；Kent Institute Australia（澳大利亚肯特学院）；Asia Pacific International College（亚太国际学院）；Worcester State University（伍斯特州立大学）；University of Kurdistan Hewler（库尔德斯坦赫勒大学）
Background and aim: Surgical telepresence using augmented perception has been applied, but mixed reality is still being researched and is only theoretical. The aim of this work is to propose a solution to improve the visualization in the final merged video by producing globally consistent videos when the intensity of illumination in the input source and target video varies. Methodology: The proposed system uses an enhanced multi-layer visualization with illumination-aware gradient mixing using Illumination Aware Video Composition algorithm. Particle Swarm Optimization Algorithm is used to find…
Visualization techniques for the decision space of continuous multi-objective optimization problems (MOPs) are rather scarce in research. For long, all techniques focused on global optimality and even for the few available landscape visualizations, e.g., cost landscapes, globality is the main criterion. In contrast, the recently proposed gradient field heatmaps (GFHs) emphasize the location and attraction basins of local efficient sets, but ignore the relation of sets in terms of solution quality. In this paper, we propose a new and hybrid visualization technique, which combines the advantages…
GastroViT: A Vision Transformer Based Ensemble Learning Approach for Gastrointestinal Disease Classification with Grad CAM & SHAP Visualization
Rajshahi University of Engineering & Technology（拉杰沙希工程技术大学）；Manchester Metropolitan University（曼彻斯特城市大学）；Qatar University（卡塔尔大学）；Universiti Kebangsaan Malaysia（马来西亚国立大学）
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…
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…
