Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification

TL;DR

This paper introduces a simple dual-granularity triplet loss for visible-thermal person re-identification, combining sample-based and center-based losses to improve intra-class compactness and inter-class discrimination, achieving significant performance gains.

Contribution

It proposes a novel hierarchical dual-granularity triplet loss that effectively integrates fine and coarse granularity levels for VT-ReID, serving as a strong baseline.

Findings

Significant performance improvement on RegDB and SYSU-MM01 datasets.

Dual-granularity triplet loss outperforms traditional methods using only global features.

Simple configurations of pooling and batch normalization suffice for effective training.

Abstract

In this letter, we propose a conceptually simple and effective dual-granularity triplet loss for visible-thermal person re-identification (VT-ReID). In general, ReID models are always trained with the sample-based triplet loss and identification loss from the fine granularity level. It is possible when a center-based loss is introduced to encourage the intra-class compactness and inter-class discrimination from the coarse granularity level. Our proposed dual-granularity triplet loss well organizes the sample-based triplet loss and center-based triplet loss in a hierarchical fine to coarse granularity manner, just with some simple configurations of typical operations, such as pooling and batch normalization. Experiments on RegDB and SYSU-MM01 datasets show that with only the global features our dual-granularity triplet loss can improve the VT-ReID performance by a significant margin. It can be a strong VT-ReID baseline to boost future research with high quality.