This paper introduces Top-GAP, a novel regularization technique that enhances the explainability and robustness of convolutional neural networks. By constraining the spatial size of the learned feature representation, our method forces the network to focus on the most salient image regions, effectively reducing background influence. Using adversarial attacks and the Effective Receptive Field, we show that Top-GAP directs more attention towards object pixels rather than the background. This leads to enhanced interpretability and robustness. We achieve over 50% robust accuracy on CIFAR-10 with PGD $ε=\frac{8}{255}$ and $20$ iterations while maintaining the original clean accuracy. Furthermore, we see increases of up to 5% accuracy against distribution shifts. Our approach also yields more precise object localization, as evidenced by up to 25% improvement in Intersection over Union (IOU) compared to methods like GradCAM and Recipro-CAM.
Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data
Fraunhofer Heinrich Hertz Institut（弗劳恩霍夫 Heinrich Hertz 研究所）；Technische Universität Berlin（柏林技术大学）；Berlin Institute for the Foundations of Learning and Data (BIFOLD)（柏林学习与数据基础研究所（BIFOLD））
Given their substantial success in addressing a wide range of computer vision challenges, Convolutional Neural Networks (CNNs) are increasingly being used in smart home applications, with many of these applications relying on the automatic recognition of human activities. In this context, low-power radar devices have recently gained in popularity as recording sensors, given that the usage of these devices allows mitigating a number of privacy concerns, a key issue when making use of conventional video cameras. Another concern that is often cited when designing smart home applications is the re…
Reliable or Deceptive? Investigating Gated Features for Smooth Visual Explanations in CNNs
Indian Institute of Information Technology Kalyani（印度卡利亚尼信息技术学院）；Jalpaiguri Government Engineering College（贾尔派古里政府工程学院）；Alipurduar Government Engineering and Management College（阿里布尔杜阿尔政府工程与管理学院）；Indian Institute of Technology Roorkee（鲁基印度理工学院）；Amazon（亚马逊）
Northeastern University（东北大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）
It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers. However, interpretability of these perturbations is less explored in the literature. This work aims to better understand the roles of adversarial perturbations and provide visual explanations from pixel, image and network perspectives. We show that adversaries have a promotion-suppression effect (PSE) on neurons' activations and can be primarily categorized into three types: i) suppression-dominated perturbations that mainly r…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance in various tasks, the interpretability is always the Achilles' heel of deep neural networks. At present, deep neural networks obtain high discrimination power at the cost of low interpretability of their black-box representations. We believe that high model interpretability may help people to break several bottlenecks of deep learning, e.g., learning from ver…
This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the used explainer. CNNs for computer vision have shown exceptional performance in critical industries. However, it is a significant barrier when deploying CNNs due to their complexity and lack of interpretability. Recent studies to explain computer vision models have shifted from extracting low-level features (pixel-based explanations) to mid-or high-level feature…
As Convolutional Neural Networks embed themselves into our everyday lives, the need for them to be interpretable increases. However, there is often a trade-off between methods that are efficient to compute but produce an explanation that is difficult to interpret, and those that are slow to compute but provide a more interpretable result. This is particularly challenging in problem spaces that require a large input volume, especially video which combines both spatial and temporal dimensions. In this work we introduce the idea of scoring superpixels through the use of gradient based pixel scori…
Graz University of Technology（格拉茨技术大学）；Infineon Technologies Austria AG（英飞凌科技奥地利股份公司）
Driver assistance systems as well as autonomous cars have to rely on sensors to perceive their environment. A heterogeneous set of sensors is used to perform this task robustly. Among them, radar sensors are indispensable because of their range resolution and the possibility to directly measure velocity. Since more and more radar sensors are deployed on the streets, mutual interference must be dealt with. In the so far unregulated automotive radar frequency band, a sensor must be capable of detecting, or even mitigating the harmful effects of interference, which include a decreased detection s…
Technical University of Kaiserslautern（凯泽斯劳滕工业大学）；Technical University of Berlin（柏林工业大学）；University of Birmingham（伯明翰大学）；NPZ Innovation GmbH（NPZ创新有限公司）；University of St.Gallen（圣加仑大学）
We propose a novel training methodology -- Concept Group Learning (CGL) -- that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept. We achieve this through a novel regularization strategy that forces filters in the same group to be active in similar image regions for a given layer. We additionally use a regularizer to encourage a sparse weighting of the concept groups in each layer so that a few concept groups can have greater importance than others. We quantitatively evaluate CGL…
University of Glasgow（格拉斯哥大学）；University of Oxford（牛津大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Deep Convolutional Neural Networks (CNNs) have been one of the most influential recent developments in computer vision, particularly for categorization. There is an increasing demand for explainable AI as these systems are deployed in the real world. However, understanding the information represented and processed in CNNs remains in most cases challenging. Within this paper, we explore the use of new information theoretic techniques developed in the field of neuroscience to enable novel understanding of how a CNN represents information. We trained a 10-layer ResNet architecture to identify 2,0…
Zurich University of Applied Sciences（苏黎世应用科技大学）；Ulm University（乌尔姆大学）
Radial basis function neural networks (RBFs) are prime candidates for pattern classification and regression and have been used extensively in classical machine learning applications. However, RBFs have not been integrated into contemporary deep learning research and computer vision using conventional convolutional neural networks (CNNs) due to their lack of adaptability with modern architectures. In this paper, we adapt RBF networks as a classifier on top of CNNs by modifying the training process and introducing a new activation function to train modern vision architectures end-to-end for imag…
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 experime…
Peter Munk Cardiac Center（彼得·芒克心脏中心）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of Waterloo（滑铁卢大学）
Medical image segmentation is a difficult but important task for many clinical operations such as cardiac bi-ventricular volume estimation. More recently, there has been a shift to utilizing deep learning and fully convolutional neural networks (CNNs) to perform image segmentation that has yielded state-of-the-art results in many public benchmark datasets. Despite the progress of deep learning in medical image segmentation, standard CNNs are still not fully adopted in clinical settings as they lack robustness and interpretability. Shapes are generally more meaningful features than solely textu…
We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model, the proposed method draws on a broad data set of visual concepts to score the semantics of hidden units at each intermediate convolutional layer. The units with semantics are given labels across a range of objects, parts, scenes, textures, materials, and colors. We use the proposed method to test the hypothesis that interpretability of units is equivalent t…
Visual interpretability of Convolutional Neural Networks (CNNs) has gained significant popularity because of the great challenges that CNN complexity imposes to understanding their inner workings. Although many techniques have been proposed to visualize class features of CNNs, most of them do not provide a correspondence between inputs and the extracted features in specific layers. This prevents the discovery of stimuli that each layer responds better to. We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most inform…
Harvard University（哈佛大学）；Imperial College London（帝国理工学院）；University of Oxford（牛津大学）
In this paper we introduce a new problem within the growing literature of interpretability for convolution neural networks (CNNs). While previous work has focused on the question of how to visually interpret CNNs, we ask what it is that we care to interpret, that is, which layers and neurons are worth our attention? Due to the vast size of modern deep learning network architectures, automated, quantitative methods are needed to rank the relative importance of neurons so as to provide an answer to this question. We present a new statistical method for ranking the hidden neurons in any convoluti…
In this paper, we propose a generic model transfer scheme to make Convlutional Neural Networks (CNNs) interpretable, while maintaining their high classification accuracy. We achieve this by building a differentiable decision forest on top of CNNs, which enjoys two characteristics: 1) During training, the tree hierarchies of the forest are learned in a top-down manner under the guidance from the category semantics embedded in the pre-trained CNN weights; 2) During inference, a single decision tree is dynamically selected from the forest for each input sample, enabling the transferred model to m…
Deep Convolutional Neural Networks (CNNs) are becoming prominent models for semi-automated diagnosis of Alzheimer's Disease (AD) using brain Magnetic Resonance Imaging (MRI). Although being highly accurate, deep CNN models lack transparency and interpretability, precluding adequate clinical reasoning and not complying with most current regulatory demands. One popular choice for explaining deep image models is occluding regions of the image to isolate their influence on the prediction. However, existing methods for occluding patches of brain scans generate images outside the distribution to whi…
Graz University of Technology（格拉茨理工大学）；Infineon Technologies Austria AG（英飞凌科技奥地利股份公司）
Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. With a rising number of radar sensors and the so far unregulated automotive radar frequency band, mutual interference is inevitable and must be dealt with. Algorithms and models operating on radar data are required to run the early processing steps on specialized radar sensor hardware. This specialized hardware typically has strict resource-constraints, i.e. a low memory capacity and low computational power. Convolutional Neural Network (CNN)-based approaches for denoising and inte…
George Mason University（乔治梅森大学）；Clarkson University（克拉克森大学）
Nowadays, the Convolutional Neural Networks (CNNs) have achieved impressive performance on many computer vision related tasks, such as object detection, image recognition, image retrieval, etc. These achievements benefit from the CNNs outstanding capability to learn the input features with deep layers of neuron structures and iterative training process. However, these learned features are hard to identify and interpret from a human vision perspective, causing a lack of understanding of the CNNs internal working mechanism. To improve the CNN interpretability, the CNN visualization is well utili…
The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. However, CNNs often criticized as being black boxes that lack interpretability, since they have millions of unexplained model parameters. In this work, we describe Network Dissection, a method that interprets networks by providing labels for the units of their deep visual representations. The proposed method quantifies the interpretability of CNN representations by evaluating the alignment between individual hidden uni…
Interpretability of Deep Neural Networks has become a major area of exploration. Although these networks have achieved state of the art accuracy in many tasks, it is extremely difficult to interpret and explain their decisions. In this work we analyze the final and penultimate layers of Deep Convolutional Networks and provide an efficient method for identifying subsets of features that contribute most towards the network's decision for a class. We demonstrate that the number of such features per class is much lower in comparison to the dimension of the final layer and therefore the decision su…
CCDepth: A Lightweight Self-supervised Depth Estimation Network with Enhanced Interpretability
College of Information Science and Engineering, China University of Petroleum (Beijing)（中国石油大学（北京）信息科学与工程学院）；The University of Hong Kong（香港大学）；Tsinghua University（清华大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
University of California, San Francisco（加利福尼亚大学旧金山分校）；University of California, Berkeley（加利福尼亚大学伯克利分校）
Deep convolutional neural networks (CNNs) have been successful in many tasks in machine vision, however, millions of weights in the form of thousands of convolutional filters in CNNs makes them difficult for human intepretation or understanding in science. In this article, we introduce CAR, a greedy structural compression scheme to obtain smaller and more interpretable CNNs, while achieving close to original accuracy. The compression is based on pruning filters with the least contribution to the classification accuracy. We demonstrate the interpretability of CAR-compressed CNNs by showing that…
Google Research, Mountain View（谷歌研究，山景城）；The Hong Kong University of Science and Technology, Hong Kong（香港科技大学，香港）
The concept of conditional computation for deep nets has been proposed previously to improve model performance by selectively using only parts of the model conditioned on the sample it is processing. In this paper, we investigate input-dependent dynamic filter selection in deep convolutional neural networks (CNNs). The problem is interesting because the idea of forcing different parts of the model to learn from different types of samples may help us acquire better filters in CNNs, improve the model generalization performance and potentially increase the interpretability of model behavior. We p…
Convolutional Neural Networks (CNNs) are propelling advances in a range of different computer vision tasks such as object detection and object segmentation. Their success has motivated research in applications of such models for medical image analysis. If CNN-based models are to be helpful in a medical context, they need to be precise, interpretable, and uncertainty in predictions must be well understood. In this paper, we develop and evaluate recent advances in uncertainty estimation and model interpretability in the context of semantic segmentation of polyps from colonoscopy images. We evalu…
Tsinghua University（清华大学）；Tsinghua SIGS（清华大学深圳国际研究生院）；Peng Cheng Lab（鹏城实验室）；ByteDance AI Lab（字节跳动人工智能实验室）；University of Southern California（南加州大学）
Convolutional neural networks (CNNs) have been successfully used in a range of tasks. However, CNNs are often viewed as "black-box" and lack of interpretability. One main reason is due to the filter-class entanglement -- an intricate many-to-many correspondence between filters and classes. Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model. In contrast, we focus on alleviating filter-class entanglement during training. Inspired by cellular differentiation, we propose a novel strategy to train interpretabl…
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…
To tackle increasingly complex tasks, it has become an essential ability of neural networks to learn abstract representations. These task-specific representations and, particularly, the invariances they capture turn neural networks into black box models that lack interpretability. To open such a black box, it is, therefore, crucial to uncover the different semantic concepts a model has learned as well as those that it has learned to be invariant to. We present an approach based on INNs that (i) recovers the task-specific, learned invariances by disentangling the remaining factor of variation i…
Michigan State University（密歇根州立大学）；Wormpex AI Research（Wormpex人工智能研究院）；ByteDance AI Lab（字节跳动人工智能实验室）
Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models to visualize how they make predictions. Recent works further push the interpretability in the network learning stage to learn more meaningful representations. In this work, focusing on a specific area of visual recognition, we report our efforts towards interpretable face recognition. We propose a spatial activation diversity loss to learn more structured fac…
The Academy for Mathematics, Science, and Engineering（数学、科学与工程学院）
Natural disasters ravage the world's cities, valleys, and shores on a regular basis. Deploying precise and efficient computational mechanisms for assessing infrastructure damage is essential to channel resources and minimize the loss of life. Using a dataset that includes labeled pre- and post- disaster satellite imagery, we take a machine learning-based remote sensing approach and train multiple convolutional neural networks (CNNs) to assess building damage on a per-building basis. We present a novel methodology of interpretable deep learning that seeks to explicitly investigate the most usef…
Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning filters in the interpretation of CNNs. We exploit our recently-proposed greedy structural compression scheme that prunes filters in a trained CNN. In our compression, the filter importance index is defined as the classification accuracy reduction (CAR) of the network after pruning t…
The focus in deep learning research has been mostly to push the limits of prediction accuracy. However, this was often achieved at the cost of increased complexity, raising concerns about the interpretability and the reliability of deep networks. Recently, an increasing attention has been given to untangling the complexity of deep networks and quantifying their uncertainty for different computer vision tasks. Differently, the task of depth completion has not received enough attention despite the inherent noisy nature of depth sensors. In this work, we thus focus on modeling the uncertainty of …
Many existing interpretation methods of convolutional neural networks (CNNs) mainly analyze in spatial domain, yet model interpretability in frequency domain has been rarely studied. To the best of our knowledge, there is no study on the interpretation of modern CNNs from the perspective of the frequency proportion of filters. In this work, we analyze the frequency properties of filters in the first layer as it is the entrance of information and relatively more convenient for analysis. By controlling the proportion of different frequency filters in the training stage, the network classificatio…
