Visual Explanation via Similar Feature Activation for Metric Learning

TL;DR

This paper introduces SFAM, a new visual explanation method for metric learning models that uses feature similarity to generate interpretability maps, addressing limitations of existing CAM-based methods.

Contribution

The paper proposes SFAM, a novel explanation technique tailored for metric learning models that lack fully connected classifier layers, utilizing similarity-based importance scores.

Findings

SFAM effectively explains CNN models using Euclidean or cosine similarity.

Experimental results show SFAM provides clear and promising visual explanations.

SFAM outperforms existing interpretability methods in the context of metric learning.

Abstract

Visual explanation maps enhance the trustworthiness of decisions made by deep learning models and offer valuable guidance for developing new algorithms in image recognition tasks. Class activation maps (CAM) and their variants (e.g., Grad-CAM and Relevance-CAM) have been extensively employed to explore the interpretability of softmax-based convolutional neural networks, which require a fully connected layer as the classifier for decision-making. However, these methods cannot be directly applied to metric learning models, as such models lack a fully connected layer functioning as a classifier. To address this limitation, we propose a novel visual explanation method termed Similar Feature Activation Map (SFAM). This method introduces the channel-wise contribution importance score (CIS) to measure feature importance, derived from the similarity measurement between two image embeddings. The explanation map is constructed by linearly combining the proposed importance weights with the feature map from a CNN model. Quantitative and qualitative experiments show that SFAM provides highly promising interpretable visual explanations for CNN models using Euclidean distance or cosine similarity as the similarity metric.