# PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification

arXiv: https://arxiv.org/abs/2203.03931 · HTML: https://mlsanity.com/paper/2203.03931/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 37 references that are in the map.
- First posted on arXiv 8 Mar 2022.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification](https://mlsanity.com/paper/2001.01526/) (2020)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [FastReID: A Pytorch Toolbox for General Instance Re-identification](https://mlsanity.com/paper/2006.02631/) (2020)
- [ABD-Net: Attentive but Diverse Person Re-Identification](https://mlsanity.com/paper/1908.01114/) (2019)
- [Self-Supervised Learning with Swin Transformers](https://mlsanity.com/paper/2105.04553/) (2021)
- [Identity-Guided Human Semantic Parsing for Person Re-Identification](https://mlsanity.com/paper/2007.13467/) (2020)
- [Unsupervised Person Re-identification via Multi-label Classification](https://mlsanity.com/paper/2004.09228/) (2020)
- [Human Semantic Parsing for Person Re-identification](https://mlsanity.com/paper/1804.00216/) (2018)
- [Unsupervised Pre-training for Person Re-identification](https://mlsanity.com/paper/2012.03753/) (2020)
- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification](https://mlsanity.com/paper/1910.12278/) (2019)
- [Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification](https://mlsanity.com/paper/2007.10315/) (2020)
- [Intra-Inter Camera Similarity for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11658/) (2021)
- [AAformer: Auto-Aligned Transformer for Person Re-Identification](https://mlsanity.com/paper/2104.00921/) (2021)

## Built on by (most cited first, 8 of 8)

- [Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks](https://mlsanity.com/paper/2303.17602/) (2023)
- [Part-Aware Transformer for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.03322/) (2023)
- [HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception](https://mlsanity.com/paper/2310.20695/) (2023)
- [Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification](https://mlsanity.com/paper/2309.01420/) (2023)
- [ProtoHPE: Prototype-guided High-frequency Patch Enhancement for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2310.07552/) (2023)
- [Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work](https://mlsanity.com/paper/2306.01929/) (2023)
- [Mutual Distillation Learning For Person Re-Identification](https://mlsanity.com/paper/2401.06430/) (2024)
- [DRFormer: A Dual-Regularized Bidirectional Transformer for Person Re-identification](https://mlsanity.com/paper/2602.01059/) (2026)

## Abstract (arXiv)

In person re-identification (ReID), very recent researches have validated pre-training the models on unlabelled person images is much better than on ImageNet. However, these researches directly apply the existing self-supervised learning (SSL) methods designed for image classification to ReID without any adaption in the framework. These SSL methods match the outputs of local views (e.g., red T-shirt, blue shorts) to those of the global views at the same time, losing lots of details. In this paper, we propose a ReID-specific pre-training method, Part-Aware Self-Supervised pre-training (PASS), which can generate part-level features to offer fine-grained information and is more suitable for ReID. PASS divides the images into several local areas, and the local views randomly cropped from each area are assigned with a specific learnable [PART] token. On the other hand, the [PART]s of all local areas are also appended to the global views. PASS learns to match the output of the local views and global views on the same [PART]. That is, the learned [PART] of the local views from a local area is only matched with the corresponding [PART] learned from the global views. As a result, each [PART] can focus on a specific local area of the image and extracts fine-grained information of this area. Experiments show PASS sets the new state-of-the-art performances on Market1501 and MSMT17 on various ReID tasks, e.g., vanilla ViT-S/16 pre-trained by PASS achieves 92.2%/90.2%/88.5% mAP accuracy on Market1501 for supervised/UDA/USL ReID. Our codes are available at https://github.com/CASIA-IVA-Lab/PASS-reID.