Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: De Marinis, Pasquale, Kaymak, Uzay, Brussee, Rogier, Vessio, Gennaro, Castellano, Giovanna
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912726015541248
author De Marinis, Pasquale
Kaymak, Uzay
Brussee, Rogier
Vessio, Gennaro
Castellano, Giovanna
author_facet De Marinis, Pasquale
Kaymak, Uzay
Brussee, Rogier
Vessio, Gennaro
Castellano, Giovanna
contents Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely opaque. While explainable AI has advanced significantly in standard computer vision tasks, interpretability in FSS remains virtually unexplored despite its critical importance for understanding model behavior and guiding support set selection in data-scarce scenarios. This paper introduces the first dedicated method for interpreting matching-based FSS models by leveraging their inherent structural properties. Our Affinity Explainer approach extracts attribution maps that highlight which pixels in support images contribute most to query segmentation predictions, using matching scores computed between support and query features at multiple feature levels. We extend standard interpretability evaluation metrics to the FSS domain and propose additional metrics to better capture the practical utility of explanations in few-shot scenarios. Comprehensive experiments on FSS benchmark datasets, using different models, demonstrate that our Affinity Explainer significantly outperforms adapted standard attribution methods. Qualitative analysis reveals that our explanations provide structured, coherent attention patterns that align with model architectures and and enable effective model diagnosis. This work establishes the foundation for interpretable FSS research, enabling better model understanding and diagnostic for more reliable few-shot segmentation systems. The source code is publicly available at https://github.com/pasqualedem/AffinityExplainer.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18163
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design
De Marinis, Pasquale
Kaymak, Uzay
Brussee, Rogier
Vessio, Gennaro
Castellano, Giovanna
Computer Vision and Pattern Recognition
Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely opaque. While explainable AI has advanced significantly in standard computer vision tasks, interpretability in FSS remains virtually unexplored despite its critical importance for understanding model behavior and guiding support set selection in data-scarce scenarios. This paper introduces the first dedicated method for interpreting matching-based FSS models by leveraging their inherent structural properties. Our Affinity Explainer approach extracts attribution maps that highlight which pixels in support images contribute most to query segmentation predictions, using matching scores computed between support and query features at multiple feature levels. We extend standard interpretability evaluation metrics to the FSS domain and propose additional metrics to better capture the practical utility of explanations in few-shot scenarios. Comprehensive experiments on FSS benchmark datasets, using different models, demonstrate that our Affinity Explainer significantly outperforms adapted standard attribution methods. Qualitative analysis reveals that our explanations provide structured, coherent attention patterns that align with model architectures and and enable effective model diagnosis. This work establishes the foundation for interpretable FSS research, enabling better model understanding and diagnostic for more reliable few-shot segmentation systems. The source code is publicly available at https://github.com/pasqualedem/AffinityExplainer.
title Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.18163