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

TL;DR

This paper introduces Affinity Explainer, a method for interpreting matching-based Few-Shot Semantic Segmentation models by highlighting pixel contributions, improving explainability, and providing insights into model behavior in data-scarce scenarios.

Contribution

It presents the first dedicated interpretability method for matching-based FSS models, leveraging their structural properties to generate meaningful explanations.

Findings

Affinity Explainer outperforms standard attribution methods in FSS

Explanations reveal structured attention patterns aligned with model architecture

Enhanced interpretability aids model diagnosis and understanding

Abstract

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.