DeepAI AI Chat
Log In Sign Up

CDPM: Convolutional Deformable Part Models for Person Re-identification

by   Kan Wang, et al.
The University of Sydney
South China University of Technology International Student Union
Birkbeck, University of London

Part-level representations are essential for robust person re-identification. Due to errors in pedestrian detection, there are usually severe mis-alignment problems for body parts, which degrade the quality of part representations. To handle this problem, we propose a novel model named Convolutional Deformable Part Models (CDPM). CDPM works by decoupling the complex part alignment procedure into two easier steps. First, a vertical alignment step detects each part in the vertical direction with the help of a multi-task learning model. Second, a horizontal refinement step based on self-attention suppresses the background information around each detected body part. Since the two steps are performed orthogonally and sequentially, the difficulty of part alignment is significantly reduced. In the testing stage, CDPM is able to accurately align flexible body parts without the need of any outside information. Extensive experimental results justify the effectiveness of CDPM for part alignment. Most impressively, CDPM achieves state-of-the-art performance on three large-scale datasets: Market-1501, DukeMTMC-ReID,and CUHK03.


page 1

page 3

page 4

page 6

page 8


Pedestrian Alignment Network for Large-scale Person Re-identification

Person re-identification (person re-ID) is mostly viewed as an image ret...

Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification

Person Re-identification (ReID) is to identify the same person across di...

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

Part-level representations are important for robust person re-identifica...

Partial Person Re-identification with Alignment and Hallucination

Partial person re-identification involves matching pedestrian frames whe...

Omni-directional Feature Learning for Person Re-identification

Person re-identification (PReID) has received increasing attention due t...

Batch Coherence-Driven Network for Part-aware Person Re-Identification

Existing part-aware person re-identification methods typically employ tw...