English
Related papers

Related papers: Score-CAM: Score-Weighted Visual Explanations for …

200 papers

Interpreting complex deep networks, notably pre-trained vision-language models (VLMs), is a formidable challenge. Current Class Activation Map (CAM) methods highlight regions revealing the model's decision-making basis but lack clear…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Yuguang Yang , Runtang Guo , Sheng Wu , Yimi Wang , Linlin Yang , Bo Fan , Jilong Zhong , Juan Zhang , Baochang Zhang

Post-hoc explanation methods, e.g., Grad-CAM, enable humans to inspect the spatial regions responsible for a particular network decision. However, it is shown that such explanations are not always consistent with human priors, such as…

Computer Vision and Pattern Recognition · Computer Science 2022-04-11 Vipin Pillai , Soroush Abbasi Koohpayegani , Ashley Ouligian , Dennis Fong , Hamed Pirsiavash

Data series classification is an important and challenging problem in data science. Explaining the classification decisions by finding the discriminant parts of the input that led the algorithm to some decisions is a real need in many…

Machine Learning · Computer Science 2022-07-26 Paul Boniol , Mohammed Meftah , Emmanuel Remy , Themis Palpanas

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…

Computer Vision and Pattern Recognition · Computer Science 2020-08-20 Ruigang Fu , Qingyong Hu , Xiaohu Dong , Yulan Guo , Yinghui Gao , Biao Li

Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates that also provide visual attention maps. Particularly, we solve for visual question…

Computer Vision and Pattern Recognition · Computer Science 2019-10-18 Badri N. Patro , Mayank Lunayach , Shivansh Patel , Vinay P. Namboodiri

To verify and validate networks, it is essential to gain insight into their decisions, limitations as well as possible shortcomings of training data. In this work, we propose a post-hoc, optimization based visual explanation method, which…

Computer Vision and Pattern Recognition · Computer Science 2019-08-08 Jörg Wagner , Jan Mathias Köhler , Tobias Gindele , Leon Hetzel , Jakob Thaddäus Wiedemer , Sven Behnke

Convolutional Neural Networks (CNNs) have seen significant performance improvements in recent years. However, due to their size and complexity, they function as black-boxes, leading to transparency concerns. State-of-the-art saliency…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Antonio De Santis , Riccardo Campi , Matteo Bianchi , Marco Brambilla

In this paper two new learning-based eXplainable AI (XAI) methods for deep convolutional neural network (DCNN) image classifiers, called L-CAM-Fm and L-CAM-Img, are proposed. Both methods use an attention mechanism that is inserted in the…

Computer Vision and Pattern Recognition · Computer Science 2022-09-23 Ioanna Gkartzonika , Nikolaos Gkalelis , Vasileios Mezaris

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…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Zhenpeng Feng , Xiyang Cui , Hongbing Ji , Mingzhe Zhu , Ljubisa Stankovic

Deep learning opacity often impedes deployment in high-stakes domains. We propose a training framework that aligns model focus with class-representative features without requiring pixel-level annotations. To this end, we introduce…

Artificial Intelligence · Computer Science 2026-02-16 Giacomo Ignesti , Davide Moroni , Massimo Martinelli

Neural networks trained to classify images do so by identifying features that allow them to distinguish between classes. These sets of features are either causal or context dependent. Grad-CAM is a popular method of visualizing both sets of…

Computer Vision and Pattern Recognition · Computer Science 2021-03-24 Mohit Prabhushankar , Ghassan AlRegib

This paper presents a novel approach to address the challenges of understanding the prediction process and debugging prediction errors in Vision Transformers (ViT), which have demonstrated superior performance in various computer vision…

Computer Vision and Pattern Recognition · Computer Science 2023-10-05 Seok-Yong Byun , Wonju Lee

Deep neural networks (DNNs) have achieved remarkable success across domains but remain difficult to interpret, limiting their trustworthiness in high-stakes applications. This paper focuses on deep vision models, for which a dominant line…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Qiming Zhao , Xingjian Li , Xiaoyu Cao , Xiaolong Wu , Min Xu

Class Activation Mapping (CAM) and its gradient-based variants (e.g., GradCAM) have become standard tools for explaining Convolutional Neural Network (CNN) predictions. However, these approaches typically focus on individual logits, while…

Machine Learning · Computer Science 2026-04-10 Jacob Piland , Chris Sweet , Adam Czajka

Convolutional neural networks (CNNs) achieve prevailing results in segmentation tasks nowadays and represent the state-of-the-art for image-based analysis. However, the understanding of the accurate decision-making process of a CNN is…

Image and Video Processing · Electrical Eng. & Systems 2024-10-01 Tillmann Rheude , Andreas Wirtz , Arjan Kuijper , Stefan Wesarg

Class activation map (CAM) has been widely used to highlight image regions that contribute to class predictions. Despite its simplicity and computational efficiency, CAM often struggles to identify discriminative regions that distinguish…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Ziheng Zhang , Jianyang Gu , Arpita Chowdhury , Zheda Mai , David Carlyn , Tanya Berger-Wolf , Yu Su , Wei-Lun Chao

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…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Miguel Lerma , Mirtha Lucas

Neural networks are becoming increasingly better at tasks that involve classifying and recognizing images. At the same time techniques intended to explain the network output have been proposed. One such technique is the Gradient-based Class…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Mirtha Lucas , Miguel Lerma , Jacob Furst , Daniela Raicu

We present a simple yet highly generalizable method for explaining interacting parts within a neural network's reasoning process. First, we design an algorithm based on cross derivatives for computing statistical interaction effects between…

Machine Learning · Computer Science 2021-10-12 Samuel Lerman , Chenliang Xu , Charles Venuto , Henry Kautz

Recently, applying deep neural networks in IR has become an important and timely topic. For instance, Neural Ranking Models(NRMs) have shown promising performance compared to the traditional ranking models. However, explaining the ranking…

Information Retrieval · Computer Science 2020-05-13 Jaekeol Choi , Jungin Choi , Wonjong Rhee