English
Related papers

Related papers: Gradient-Based Interpretability Methods and Binari…

200 papers

Deep Neural Networks (DNNs) are expected to provide explanation for users to understand their black-box predictions. Saliency map is a common form of explanation illustrating the heatmap of feature attributions, but it suffers from noise in…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Rui Xu , Wenkang Qin , Peixiang Huang , Hao Wang , Lin Luo

Explainability is a vital aspect of modern AI for real-world impact and usability. The main objective of this paper is to emphasise the need to understand the predictions of Computer Vision models, specifically Convolutional Neural Network…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Ravidu Suien Rammuni Silva , Jordan J. Bird

Deep Neural Networks (DNNs) have become very popular for prediction in many areas. Their strength is in representation with a high number of parameters that are commonly learned via gradient descent or similar optimization methods. However,…

Machine Learning · Statistics 2016-10-11 Anthony Caterini , Dong Eui Chang

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…

Computer Vision and Pattern Recognition · Computer Science 2020-09-29 Alfred Schöttl

Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can jointly learn node representations and coarsen the graph.…

Machine Learning · Computer Science 2020-06-11 Amir Hosein Khasahmadi , Kaveh Hassani , Parsa Moradi , Leo Lee , Quaid Morris

Graph Neural Networks (GNNs) have emerged as an efficient alternative to convolutional approaches for vision tasks such as image classification, leveraging patch-based representations instead of raw pixels. These methods construct graphs…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Nikolaos Chaidos , Angeliki Dimitriou , Nikolaos Spanos , Athanasios Voulodimos , Giorgos Stamou

Recent brain tumor classification methods often report high accuracy but rely on deep, over-parameterized architectures with limited interpretability, making it difficult to determine whether predictions are driven by tumor-relevant…

Image and Video Processing · Electrical Eng. & Systems 2026-03-24 Rajan Das Gupta , Md Imrul Hasan Showmick , Lei Wei , Mushfiqur Rahman Abir , Shanjida Akter , Md. Yeasin Rahat , Md. Jakir Hossen

Saliency methods seek to explain the predictions of a model by producing an importance map across each input sample. A popular class of such methods is based on backpropagating a signal and analyzing the resulting gradient. Despite much…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Sylvestre-Alvise Rebuffi , Ruth Fong , Xu Ji , Andrea Vedaldi

Gradient-based saliency maps have been widely used to explain the decisions of deep neural network classifiers. However, standard gradient-based interpretation maps, including the simple gradient and integrated gradient algorithms, often…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Shizhan Gong , Qi Dou , Farzan Farnia

Graph Neural Networks (GNNs) are gaining extensive attention for their application in graph data. However, the black-box nature of GNNs prevents users from understanding and trusting the models, thus hampering their applicability. Whereas…

Machine Learning · Computer Science 2023-05-23 Qizhang Feng , Ninghao Liu , Fan Yang , Ruixiang Tang , Mengnan Du , Xia Hu

The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation. The inherent complexity of input features, notably pixels extracted from images, engenders complex correlations.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-16 Caroline Mazini Rodrigues , Nicolas Boutry , Laurent Najman

Explaining the predictions of deep neural nets has been a topic of great interest in the computer vision literature. While several gradient-based interpretation schemes have been proposed to reveal the influential variables in a neural…

Computer Vision and Pattern Recognition · Computer Science 2023-02-13 Jingwei Zhang , Farzan Farnia

Graph Neural Networks (GNNs) have emerged as the predominant approach for learning over graph-structured data. However, most GNNs operate as black-box models and require post-hoc explanations, which may not suffice in high-stakes scenarios…

Machine Learning · Computer Science 2025-10-14 Maya Bechler-Speicher , Amir Globerson , Ran Gilad-Bachrach

Current methods for the interpretability of discriminative deep neural networks commonly rely on the model's input-gradients, i.e., the gradients of the output logits w.r.t. the inputs. The common assumption is that these input-gradients…

Machine Learning · Computer Science 2021-03-04 Suraj Srinivas , Francois Fleuret

Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically…

Image and Video Processing · Electrical Eng. & Systems 2021-06-29 Zixuan Liu , Ehsan Adeli , Kilian M. Pohl , Qingyu Zhao

Understanding the flow of information in Deep Neural Networks (DNNs) is a challenging problem that has gain increasing attention over the last few years. While several methods have been proposed to explain network predictions, there have…

Machine Learning · Computer Science 2018-03-08 Marco Ancona , Enea Ceolini , Cengiz Öztireli , Markus Gross

Interpretability methods for deep neural networks mainly focus on the sensitivity of the class score with respect to the original or perturbed input, usually measured using actual or modified gradients. Some methods also use a…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Md Mahfuzur Rahman , Noah Lewis , Sergey Plis

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions…

Machine Learning · Computer Science 2017-11-28 Andrew Slavin Ross , Finale Doshi-Velez

Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypotheses were…

Machine Learning · Computer Science 2019-09-17 Beomsu Kim , Junghoon Seo , SeungHyun Jeon , Jamyoung Koo , Jeongyeol Choe , Taegyun Jeon

How can we learn effective node representations on textual graphs? Graph Neural Networks (GNNs) that use Language Models (LMs) to encode textual information of graphs achieve state-of-the-art performance in many node classification tasks.…