Enregistré dans:
Détails bibliographiques
Auteurs principaux: Vandenhirtz, Moritz, Vogt, Julia E.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.06003
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910946830581760
author Vandenhirtz, Moritz
Vogt, Julia E.
author_facet Vandenhirtz, Moritz
Vogt, Julia E.
contents Understanding the decision-making process of machine learning models provides valuable insights into the task, the data, and the reasons behind a model's failures. In this work, we propose a method that performs inherently interpretable predictions through the instance-wise sparsification of input images. To align the sparsification with human perception, we learn the masking in the space of semantically meaningful pixel regions rather than on pixel-level. Additionally, we introduce an explicit way to dynamically determine the required level of sparsity for each instance. We show empirically on semi-synthetic and natural image datasets that our inherently interpretable classifier produces more meaningful, human-understandable predictions than state-of-the-art benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06003
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
Vandenhirtz, Moritz
Vogt, Julia E.
Computer Vision and Pattern Recognition
Machine Learning
Understanding the decision-making process of machine learning models provides valuable insights into the task, the data, and the reasons behind a model's failures. In this work, we propose a method that performs inherently interpretable predictions through the instance-wise sparsification of input images. To align the sparsification with human perception, we learn the masking in the space of semantically meaningful pixel regions rather than on pixel-level. Additionally, we introduce an explicit way to dynamically determine the required level of sparsity for each instance. We show empirically on semi-synthetic and natural image datasets that our inherently interpretable classifier produces more meaningful, human-understandable predictions than state-of-the-art benchmarks.
title From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.06003