Contrastive Bayesian Analysis for Deep Metric Learning

TL;DR

This paper introduces a contrastive Bayesian analysis framework for deep metric learning, developing a novel loss function that effectively bridges the semantic gap between features and labels, leading to improved performance.

Contribution

The paper proposes a new contrastive Bayesian loss function and a metric variance constraint to enhance deep metric learning, especially in generalizing to new classes.

Findings

Significant performance improvements over existing methods.

Effective in both supervised and pseudo-supervised scenarios.

Ablation studies validate the components of the proposed method.

Abstract

Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same class closer and push negative samples from different classes away from each other. In this work, we recognize that there is a significant semantic gap between features at the intermediate feature layer and class labels at the final output layer. To bridge this gap, we develop a contrastive Bayesian analysis to characterize and model the posterior probabilities of image labels conditioned by their features similarity in a contrastive learning setting. This contrastive Bayesian analysis leads to a new loss function for deep metric learning. To improve the generalization capability of the proposed method onto new classes, we further extend the contrastive Bayesian loss with a metric variance constraint. Our experimental results and ablation studies demonstrate that the proposed contrastive Bayesian metric learning method significantly improves the performance of deep metric learning in both supervised and pseudo-supervised scenarios, outperforming existing methods by a large margin.