Yongxia Li

2 months ago | nature.com | Yongxia Li |Jianguang Zhang |Jiajia Guo |Qi Guo |Weihao Qin |Xianbin Wen

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.

Dec 25, 2023 | mdpi.com | Yongxia Li |Wenzhe Wang |Changxuan Liu |Min Zeng

All articles published by MDPI are made immediately available worldwide under an open access license. No specialpermission is required to reuse all or part of the article published by MDPI, including figures and tables. Forarticles published under an open access Creative Common CC BY license, any part of the article may be reused withoutpermission provided that the original article is clearly cited. For more information, please refer tohttps://www.mdpi.com/openaccess.