Visual Explanation Via Similar Feature Activation For 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 featur

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliao2025visual

Related papers

• Visual Explanation For Deep Metric Learning (2019)14.36
• Feature Activation Map: Visual Explanation Of Deep Learning Models For Image Classification (2023)0.00
• Towards Visually Explaining Similarity Models (2020)0.00
• Visual Similarity Attention (2019)0.00
• Class-weighted Convolutional Features For Visual Instance Search (2017)12.81
• Explaining Similarity In Vision-language Encoders With Weighted Banzhaf Interactions (2025)0.00
• Visualizing Deep Similarity Networks (2019)11.85
• Attributable Visual Similarity Learning (2022)11.68