Attention-based hybrid contrastive learning for unsupervised person re-identification

Existing unsupervised Re-ID methods often rely on pseudo-labels generated by clustering algorithms. However, the effectiveness of these methods is highly dependent on the quality of the learned features. As a result, improving the quality of the extracted features will highly enhance the performance of the model. In this paper, an attention-based hybrid contrastive learning method (AHCL) is proposed by incorporating a novel attention mechanism, which combines spatial attention and channel attention to enable the model to learn more effective features. Additionally, a hybrid contrastive learning approach is introduced, which utilizes a memory dictionary to store features and extracts both cluster-level and instance-level features for contrastive learning. For cluster-level contrastive loss, it ensures that the network is updated in a more stable way by comparing the sample with the cluster center. Meanwhile, it can extract more discriminative information by comparing the sample with hard samples in instance-level contrastive loss. Thus, the performance of the model would be improved by using the combination of this two loss. The experimental results on three widely-used large-scale Re-ID datasets and experimental settings demonstrate that the proposed AHCL outperforms the compared existing methods and significantly enhances the accuracy of unsupervised person Re-identification.