Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification

Lisha Tang, Yi Wang, Lap Pui Chau

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

Vehicle re-identification (Re-ID) aims to retrieve images with the same vehicle ID across different cameras. Current part-level feature learning methods typically detect vehicle parts via uniform division, outside tools, or attention modeling. However, such part features often require expensive additional annotations and cause sub-optimal performance in case of unreliable part mask predictions. In this paper, we propose a weakly-supervised Part-Attention Network (PANet) and Part-Mentored Network (PMNet) for Vehicle Re-ID. Firstly, PANet localizes vehicle parts via part-relevant channel recalibration and cluster-based mask generation without vehicle part supervisory information. Secondly, PMNet leverages teacher-student guided learning to distill vehicle part-specific features from PANet and performs multi-scale global-part feature extraction. During inference, PMNet can adaptively extract discriminative part features without part localization by PANet, preventing unstable part mask predictions. We address this Re-ID issue as a multi-task problem and adopt Homoscedastic Uncertainty to learn the optimal weighing of ID losses. Experiments are conducted on two public benchmarks, showing that our approach outperforms recent methods, which require no extra annotations by an average increase of 3.0% in CMC@5 on VehicleID and over 1.4% in mAP on VeRi776. Moreover, our method can extend to the occluded vehicle Re-ID task and exhibits good generalization ability.

Original languageEnglish
Article number9853621
Pages (from-to)1-12
JournalIEEE Transactions on Circuits and Systems for Video Technology
DOIs
Publication statusAccepted/In press - 2022

Keywords

  • Annotations
  • attention
  • Clutter
  • Feature extraction
  • Lighting
  • Location awareness
  • multi-task learning
  • Representation learning
  • Task analysis
  • Vehicle re-identification
  • weak supervision

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification'. Together they form a unique fingerprint.

Cite this