Saved in:
Bibliographic Details
Main Authors: Kim, Soyeon, Lim, Seongwoo, Lee, Kyowoon, Choi, Jaesik
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.19607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911698282086400
author Kim, Soyeon
Lim, Seongwoo
Lee, Kyowoon
Choi, Jaesik
author_facet Kim, Soyeon
Lim, Seongwoo
Lee, Kyowoon
Choi, Jaesik
contents Integrated Gradients (IG) is a widely adopted feature attribution method that satisfies desirable axiomatic properties. However, the choice of integration path significantly affects the quality of attributions, and the standard straight-line path introduces all input features simultaneously, often accumulating noisy gradients along the way. To address this limitation, we propose Spectral Integrated Gradients, which constructs integration paths based on singular value decomposition (SVD) of the baseline-to-input difference. By progressively activating singular components from largest to smallest, SIG introduces global structure before fine-grained details, naturally following a coarse-to-fine progression. Through extensive evaluation across diverse image classification datasets, we demonstrate that SIG produces cleaner attribution maps with reduced noise and achieves improved quantitative performance compared to existing path-based attribution methods. Our code is available at https://github.com/leekwoon/sig/.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19607
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution
Kim, Soyeon
Lim, Seongwoo
Lee, Kyowoon
Choi, Jaesik
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
68T07, 68T05, 68T45
I.2.6; I.5.2; I.2.10
Integrated Gradients (IG) is a widely adopted feature attribution method that satisfies desirable axiomatic properties. However, the choice of integration path significantly affects the quality of attributions, and the standard straight-line path introduces all input features simultaneously, often accumulating noisy gradients along the way. To address this limitation, we propose Spectral Integrated Gradients, which constructs integration paths based on singular value decomposition (SVD) of the baseline-to-input difference. By progressively activating singular components from largest to smallest, SIG introduces global structure before fine-grained details, naturally following a coarse-to-fine progression. Through extensive evaluation across diverse image classification datasets, we demonstrate that SIG produces cleaner attribution maps with reduced noise and achieves improved quantitative performance compared to existing path-based attribution methods. Our code is available at https://github.com/leekwoon/sig/.
title Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
68T07, 68T05, 68T45
I.2.6; I.5.2; I.2.10
url https://arxiv.org/abs/2605.19607