Visual Explanation via Similar Feature Activation for Metric Learning
This work addresses the interpretability gap for metric learning in image recognition, offering a novel solution for researchers and practitioners, though it is incremental as it adapts existing CAM concepts to a new model type.
The paper tackles the problem of generating visual explanations for metric learning models, which lack a fully connected layer, by proposing the Similar Feature Activation Map (SFAM) method, which uses channel-wise importance scores based on similarity measurements to produce interpretable visual maps.
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.