Towards Interpretable Deep Metric Learning with Structural Matching

TL;DR

This paper introduces a structural matching approach for deep metric learning that improves interpretability by explicitly aligning spatial features, enabling more transparent similarity assessments between images.

Contribution

The proposed DIML method incorporates explicit spatial alignment into deep metric learning, enhancing interpretability and compatibility with existing models.

Findings

Achieves better interpretability of image similarity

Substantially improves performance on benchmark datasets

Compatible with various backbone networks

Abstract

How do the neural networks distinguish two images? It is of critical importance to understand the matching mechanism of deep models for developing reliable intelligent systems for many risky visual applications such as surveillance and access control. However, most existing deep metric learning methods match the images by comparing feature vectors, which ignores the spatial structure of images and thus lacks interpretability. In this paper, we present a deep interpretable metric learning (DIML) method for more transparent embedding learning. Unlike conventional metric learning methods based on feature vector comparison, we propose a structural matching strategy that explicitly aligns the spatial embeddings by computing an optimal matching flow between feature maps of the two images. Our method enables deep models to learn metrics in a more human-friendly way, where the similarity of two images can be decomposed to several part-wise similarities and their contributions to the overall similarity. Our method is model-agnostic, which can be applied to off-the-shelf backbone networks and metric learning methods. We evaluate our method on three major benchmarks of deep metric learning including CUB200-2011, Cars196, and Stanford Online Products, and achieve substantial improvements over popular metric learning methods with better interpretability. Code is available at https://github.com/wl-zhao/DIML