# Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification

arXiv: https://arxiv.org/abs/2003.08069 · HTML: https://mlsanity.com/paper/2003.08069/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2020.

## Built on by (most cited first, 23 of 23)

- [Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification](https://mlsanity.com/paper/2107.12666/) (2021)
- [Learning Granularity-Unified Representations for Text-to-Image Person Re-identification](https://mlsanity.com/paper/2207.07802/) (2022)
- [Person Re-Identification with a Locally Aware Transformer](https://mlsanity.com/paper/2106.03720/) (2021)
- [Quality-aware Part Models for Occluded Person Re-identification](https://mlsanity.com/paper/2201.00107/) (2022)
- [Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification](https://mlsanity.com/paper/2108.09682/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [A Versatile Framework for Multi-scene Person Re-identification](https://mlsanity.com/paper/2403.11121/) (2024)
- [Graph Convolution Based Efficient Re-Ranking for Visual Retrieval](https://mlsanity.com/paper/2306.08792/) (2023)
- [G2DA: Geometry-Guided Dual-Alignment Learning for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2106.07853/) (2021)
- [Style Interleaved Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2207.03132/) (2022)
- [Graph Convolution for Re-ranking in Person Re-identification](https://mlsanity.com/paper/2107.02220/) (2021)
- [Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification](https://mlsanity.com/paper/2406.16042/) (2024)
- [Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs](https://mlsanity.com/paper/2305.19844/) (2023)
- [Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification](https://mlsanity.com/paper/2207.14243/) (2022)
- [BPJDet: Extended Object Representation for Generic Body-Part Joint Detection](https://mlsanity.com/paper/2304.10765/) (2023)
- [Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification](https://mlsanity.com/paper/2107.08228/) (2021)
- [Context Sensing Attention Network for Video-based Person Re-identification](https://mlsanity.com/paper/2207.02631/) (2022)
- [SCLNet: A Scale-Robust Complementary Learning Network for Object Detection in UAV Images](https://mlsanity.com/paper/2409.07024/) (2024)
- [Self-Supervised Modality-Aware Multiple Granularity Pre-Training for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2112.06147/) (2021)
- [End-to-End Context-Aided Unicity Matching for Person Re-identification](https://mlsanity.com/paper/2210.12008/) (2022)
- [Prototype-guided Cross-modal Completion and Alignment for Incomplete Text-based Person Re-identification](https://mlsanity.com/paper/2309.17104/) (2023)
- [DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification](https://mlsanity.com/paper/2401.18032/) (2024)
- [Reliability-Aware 3D Geometric Injection for Universal Person Re-identification](https://mlsanity.com/paper/2607.18863/) (2026)

## Abstract (arXiv)

Part-level representations are important for robust person re-identification (ReID), but in practice feature quality suffers due to the body part misalignment problem. In this paper, we present a robust, compact, and easy-to-use method called the Multi-task Part-aware Network (MPN), which is designed to extract semantically aligned part-level features from pedestrian images. MPN solves the body part misalignment problem via multi-task learning (MTL) in the training stage. More specifically, it builds one main task (MT) and one auxiliary task (AT) for each body part on the top of the same backbone model. The ATs are equipped with a coarse prior of the body part locations for training images. ATs then transfer the concept of the body parts to the MTs via optimizing the MT parameters to identify part-relevant channels from the backbone model. Concept transfer is accomplished by means of two novel alignment strategies: namely, parameter space alignment via hard parameter sharing and feature space alignment in a class-wise manner. With the aid of the learned high-quality parameters, MTs can independently extract semantically aligned part-level features from relevant channels in the testing stage. MPN has three key advantages: 1) it does not need to conduct body part detection in the inference stage; 2) its model is very compact and efficient for both training and testing; 3) in the training stage, it requires only coarse priors of body part locations, which are easy to obtain. Systematic experiments on four large-scale ReID databases demonstrate that MPN consistently outperforms state-of-the-art approaches by significant margins. Code is available at https://github.com/WangKan0128/MPN.