Global-Supervised Contrastive Loss and View-Aware-Based Post-Processing for Vehicle Re-Identification

TL;DR

This paper introduces a global-supervised contrastive loss for vehicle re-identification and a view-aware post-processing method that enhances existing models without retraining, improving accuracy and robustness.

Contribution

It presents a novel global-supervised contrastive loss and a view-aware post-processing technique for vehicle re-id, which can be applied to existing models during testing.

Findings

Global-supervised contrastive loss improves feature discrimination.

VABPP enhances re-id performance when applied as post-processing.

Method is compatible with various trained models.

Abstract

In this paper, we propose a Global-Supervised Contrastive loss and a view-aware-based post-processing (VABPP) method for the field of vehicle re-identification. The traditional supervised contrastive loss calculates the distances of features within the batch, so it has the local attribute. While the proposed Global-Supervised Contrastive loss has new properties and has good global attributes, the positive and negative features of each anchor in the training process come from the entire training set. The proposed VABPP method is the first time that the view-aware-based method is used as a post-processing method in the field of vehicle re-identification. The advantages of VABPP are that, first, it is only used during testing and does not affect the training process. Second, as a post-processing method, it can be easily integrated into other trained re-id models. We directly apply the view-pair distance scaling coefficient matrix calculated by the model trained in this paper to another trained re-id model, and the VABPP method greatly improves its performance, which verifies the feasibility of the VABPP method.