ConMAE: Contour Guided MAE for Unsupervised Vehicle Re-Identification

TL;DR

This paper introduces ConMAE, a contour-guided masked autoencoder that enhances unsupervised vehicle re-identification by focusing on key contour regions, improving cross-view generalization without relying on large annotated datasets.

Contribution

The work proposes a novel contour-guided MAE framework with a label softening strategy for improved unsupervised vehicle re-identification performance.

Findings

Significant performance gains on VeRi-776 and VehicleID datasets.

Effective extraction of key contour features for cross-view matching.

Outperforms existing unsupervised methods in vehicle re-identification.

Abstract

Vehicle re-identification is a cross-view search task by matching the same target vehicle from different perspectives. It serves an important role in road-vehicle collaboration and intelligent road control. With the large-scale and dynamic road environment, the paradigm of supervised vehicle re-identification shows limited scalability because of the heavy reliance on large-scale annotated datasets. Therefore, the unsupervised vehicle re-identification with stronger cross-scene generalization ability has attracted more attention. Considering that Masked Autoencoder (MAE) has shown excellent performance in self-supervised learning, this work designs a Contour Guided Masked Autoencoder for Unsupervised Vehicle Re-Identification (ConMAE), which is inspired by extracting the informative contour clue to highlight the key regions for cross-view correlation. ConMAE is implemented by preserving the image blocks with contour pixels and randomly masking the blocks with smooth textures. In addition, to improve the quality of pseudo labels of vehicles for unsupervised re-identification, we design a label softening strategy and adaptively update the label with the increase of training steps. We carry out experiments on VeRi-776 and VehicleID datasets, and a significant performance improvement is obtained by the comparison with the state-of-the-art unsupervised vehicle re-identification methods. The code is available on the website of https://github.com/2020132075/ConMAE.