# Learning Diverse Features with Part-Level Resolution for Person Re-Identification

arXiv: https://arxiv.org/abs/2001.07442 · HTML: https://mlsanity.com/paper/2001.07442/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2020.

## Built on by (most cited first, 9 of 9)

- [ACE-Step: A Step Towards Music Generation Foundation Model](https://mlsanity.com/paper/2506.00045/) (2025)
- [Person Re-Identification with a Locally Aware Transformer](https://mlsanity.com/paper/2106.03720/) (2021)
- [Lightweight Multi-Branch Network for Person Re-Identification](https://mlsanity.com/paper/2101.10774/) (2021)
- [Benchmarks for Corruption Invariant Person Re-identification](https://mlsanity.com/paper/2111.00880/) (2021)
- [Neighbourhood-guided Feature Reconstruction for Occluded Person Re-Identification](https://mlsanity.com/paper/2105.07345/) (2021)
- [Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification](https://mlsanity.com/paper/2102.09321/) (2021)
- [Specialized Re-Ranking: A Novel Retrieval-Verification Framework for Cloth Changing Person Re-Identification](https://mlsanity.com/paper/2210.03592/) (2022)
- [FPB: Feature Pyramid Branch for Person Re-Identification](https://mlsanity.com/paper/2108.01901/) (2021)
- [On-the-Fly Homographies Calibration for Multi-Camera Tracking](https://mlsanity.com/paper/2609.18582/) (2026)

## Abstract (arXiv)

Learning diverse features is key to the success of person re-identification. Various part-based methods have been extensively proposed for learning local representations, which, however, are still inferior to the best-performing methods for person re-identification. This paper proposes to construct a strong lightweight network architecture, termed PLR-OSNet, based on the idea of Part-Level feature Resolution over the Omni-Scale Network (OSNet) for achieving feature diversity. The proposed PLR-OSNet has two branches, one branch for global feature representation and the other branch for local feature representation. The local branch employs a uniform partition strategy for part-level feature resolution but produces only a single identity-prediction loss, which is in sharp contrast to the existing part-based methods. Empirical evidence demonstrates that the proposed PLR-OSNet achieves state-of-the-art performance on popular person Re-ID datasets, including Market1501, DukeMTMC-reID and CUHK03, despite its small model size.