Catalyst for Clustering-Based Unsupervised Object Re-identification: Feature Calibration
DOI:
https://doi.org/10.1609/aaai.v38i4.28092Keywords:
CV: Representation Learning for Vision, CV: Image and Video Retrieval, ML: Clustering, ML: Unsupervised & Self-Supervised LearningAbstract
Clustering-based methods are emerging as a ubiquitous technology in unsupervised object Re-Identification (ReID), which alternate between pseudo-label generation and representation learning. Recent advances in this field mainly fall into two groups: pseudo-label correction and robust representation learning. Differently, in this work, we improve unsupervised object ReID from feature calibration, a completely different but complementary insight from the current approaches. Specifically, we propose to insert a conceptually simple yet empirically powerful Feature Calibration Module (FCM) before pseudo-label generation. In practice, FCM calibrates the features using a nonparametric graph attention network, enforcing similar instances to move together in the feature space while allowing dissimilar instances to separate. As a result, we can generate more reliable pseudo-labels using the calibrated features and further improve subsequent representation learning. FCM is simple, effective, parameter-free, training-free, plug-and-play, and can be considered as a catalyst, increasing the ’chemical reaction’ between pseudo-label generation and representation learning. Moreover, it maintains the efficiency of testing time with negligible impact on training time. In this paper, we insert FCM into a simple baseline. Experiments across different scenarios and benchmarks show that FCM consistently improves the baseline (e.g., 8.2% mAP gain on MSMT17), and achieves the new state-of-the-art results. Code is available at: https://github.com/lhf12278/FCM-ReID.Downloads
Published
2024-03-24
How to Cite
Li, H., Hu, Q., & Hu, Z. (2024). Catalyst for Clustering-Based Unsupervised Object Re-identification: Feature Calibration. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3091-3099. https://doi.org/10.1609/aaai.v38i4.28092
Issue
Section
AAAI Technical Track on Computer Vision III