# Learning Incremental Triplet Margin for Person Re-identification

## TL;DR

This paper introduces an incremental triplet margin learning strategy with multi-stage training and hard identity sampling to enhance person re-identification performance, demonstrating significant improvements over existing methods.

## Contribution

It proposes a novel multi-stage training approach that learns incremental triplet margins and utilizes global hard identity searching for better feature discrimination.

## Key findings

- Outperforms most state-of-the-art methods on Market-1501, CUHK03, and DukeMTMCreID datasets.
- Shows that larger triplet margins improve person re-identification accuracy.
- Utilizes multi-level feature maps for more discriminative features.

## Abstract

Person re-identification (ReID) aims to match people across multiple non-overlapping video cameras deployed at different locations. To address this challenging problem, many metric learning approaches have been proposed, among which triplet loss is one of the state-of-the-arts. In this work, we explore the margin between positive and negative pairs of triplets and prove that large margin is beneficial. In particular, we propose a novel multi-stage training strategy which learns incremental triplet margin and improves triplet loss effectively. Multiple levels of feature maps are exploited to make the learned features more discriminative. Besides, we introduce global hard identity searching method to sample hard identities when generating a training batch. Extensive experiments on Market-1501, CUHK03, and DukeMTMCreID show that our approach yields a performance boost and outperforms most existing state-of-the-art methods.