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

TL;DR

This paper introduces a weakly-supervised approach for vehicle re-identification that localizes vehicle parts without extra annotations and leverages teacher-student learning to improve feature extraction, outperforming recent methods.

Contribution

Proposes PANet and PMNet for vehicle Re-ID that localize parts without supervision and distill part-specific features using guided learning, enhancing performance and robustness.

Findings

Outperforms recent methods on VehicleID and VeRi776 benchmarks.

Achieves 3.0% higher CMC@5 and 1.4% higher mAP.

Demonstrates good generalization and effectiveness in occluded vehicle Re-ID.

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.