paper-with-me

Papers

Evaluating Feature Attribution Methods in the Image Domain

2022-02-22 · Arne Gevaert, Axel-Jan Rousseau, Thijs Becker, Dirk Valkenborg, Tijl De Bie, Yvan Saeys

Feature attribution maps are a popular approach to highlight the most important pixels in an image for a given prediction of a model. Despite a recent growth in popularity and available methods, little attention is given to the objective evaluation of such attribution maps. Building on previous work in this domain, we investigate existing metrics and propose new variants of metrics for the evaluation of attribution maps. We confirm a recent finding that different attribution metrics seem to measure different underlying concepts of attribution maps, and extend this finding to a larger selection of attribution metrics. We also find that metric results on one dataset do not necessarily generalize to other datasets, and methods with desirable theoretical properties such as DeepSHAP do not necessarily outperform computationally cheaper alternatives. Based on these findings, we propose a general benchmarking approach to identify the ideal feature attribution method for a given use case. Implementations of attribution metrics and our experiments are available online.

📄 PDF Abstract BibTeX arXiv:2202.12270

Code (2)

arnegevaert/benchmark-general-imaging 공식 구현 pytorch
zoeparman/benchmark-general-imaging 공식 구현 pytorch

Tasks

Benchmarking

Similar Papers 제목 키워드 기반

Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods

2025-12-07 · Panagiota Kiourti, Anu Singh, Preeti Duraipandian, Weichao Zhou 외 arxiv

This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and intro…

Greedy PIG: Adaptive Integrated Gradients

2023-11-10 · Kyriakos Axiotis, Sami Abu-al-haija, Lin Chen, Matthew Fahrbach 외

Deep learning has become the standard approach for most machine learning tasks. While its impact is undeniable, interpreting the predictions of deep learning models from a human perspective remains a challenge. In contra…

Deep Learningfeature selection

Fourier Feature Attribution: A New Efficiency Attribution Method

2025-04-02 · Zechen Liu, Feiyang Zhang, Wei Song, Xiang Li 외

The study of neural networks from the perspective of Fourier features has garnered significant attention. While existing analytical research suggests that neural networks tend to learn low-frequency features, a clear att…

feature selectionSpecificity

Class-Dependent Perturbation Effects in Evaluating Time Series Attributions

2025-02-24 · Gregor Baer, Isel Grau, Chao Zhang, Pieter Van Gorp

As machine learning models become increasingly prevalent in time series applications, Explainable Artificial Intelligence (XAI) methods are essential for understanding their predictions. Within XAI, feature attribution m…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Time SeriesTime Series Classification

Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain

2023-05-24 · Gabriel Kasmi, Laurent Dubus, Yves-Marie Saint Drenan, Philippe Blanc

Neural networks have shown remarkable performance in computer vision, but their deployment in numerous scientific and technical fields is challenging due to their black-box nature. Scientists and practitioners need to ev…