Joint label refinement and contrastive learning with hybrid memory for Unsupervised Marine Object Re-Identification
Xiaorui Han, Zhiqi Chen, Ruixue Wang, Pengfei Zhao · 2021
Unsupervised object re-identification is a challenging task due to the missing of labels for the dataset. Many unsupervised object re-identification approaches combine clustering-based pseudo-label prediction with feature fine-tuning. These methods have achieved great success in the field of unsupervised object Re-ID. However, the inevitable label noise caused by the clustering procedure was ignored. Such noisy pseudo labels substantially hinder the model’s capability on further improving feature representations. To this end, we propose a novel joint label refinement and contrastive learning framework with hybrid memory to alleviate this problem. Firstly, in order to reduce the noise of clustering pseudo labels, we propose a novel noise refinement strategy. This strategy refines pseudo labels at clustering phase and promotes clustering quality by boosting the label purity. In addition, we propose a hybrid memory bank. The hybrid memory dynamically generates prototype-level and un-clustered instance-level supervisory signals for learning feature representations. With all prototype-level and un-clustered instance-level supervisions, re-identification model is trained progressively. Our proposed unsupervised object Re-ID framework significantly reduces the influence of noisy labels and refines the learned features. Our method consistently achieves state-of-the-art performance on benchmark datasets.