Multi-Task Learning With Coarse Priors for Robust Part-Aware Person Re-Identification

2020/03/31 by Changxing Ding, Kan Wang, Pengfei Wang +1 · 101 citations
Computer Science · Engineering · #Artificial intelligence #Bayesian probability #Computer science #Engineering #Face recognition and analysis #Gait Recognition and Analysis #Identification (biology) #Machine learning #Pattern recognition (psychology) #Prior probability #Robustness (evolution) #Task (project management) #Video Surveillance and Tracking Methods #cs.CV

paper · pdf · doi:10.1109/tpami.2020.3024900

published in IEEE Transactions on Pattern Analysis and Machine Intelligence 44(3), 1474-1488 (IEEE Computer Society) · Accepted Version to IEEE Transactions on Pattern Analysis and Machine Intelligence

openalex publication_date 2020/09/18 · arxiv created 2021/05/07 · arxiv updated 2021/05/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

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.

Citations

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Learning Transferable Features with Deep Adaptation Networks
• Person Re-identification: Past, Present and Future
• In Defense of the Triplet Loss for Person Re-Identification
• SVDNet for Pedestrian Retrieval
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• An Overview of Multi-Task Learning in Deep Neural Networks
• Random Erasing Data Augmentation
• GLAD
• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Factorized Distillation: Training Holistic Person Re-identification Model by Distilling an Ensemble of Partial ReID Models
• Pose-Invariant Embedding for Deep Person Re-Identification
• Random Erasing Data Augmentation
• Relation-Aware Global Attention for Person Re-identification
• A Discriminatively Learned CNN Embedding for Person Reidentification
• Resource Aware Person Re-identification across Multiple Resolutions
• Squeeze-and-Excitation Networks