A model with pseudo-label correction and distribution alignment for image clustering. (December 2022)

• Record Type: Journal Article
• Authors: Zhang, Feng; Liu, Zi Wei; Lim, Chee Peng; Dong, Chun-Ru; Hua, Qiang
• Is Part Of: Computers & electrical engineering. Volume 104:Part B(2022)
• Publication Date: 2022-12
• Subjects: Pseudo-label correction -- Distribution alignment -- Image clustering -- Contrastive learning; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108457
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: PCDAC corrects pseudo-label errors. can be applied to large-scale online scenarios. DA realizes pseudo-label refining. Abstract: Self-supervised learning has recently created a surge of research interest in image clustering with the help of pseudo-labels. However, most of methods have to face the challenge of dealing with noisy labels since the noisy pseudo-labels might provide erroneous guidance for model training and deteriorate the clustering performance. To solve this problem, a Pseudo-label Correction and Distribution Alignment-based deep Clustering (PCDAC) model is proposed in this paper. To correct the noisy pseudo-labels, PCDAC embeds the historical cluster assignment by maintaining a memory bank. Additionally, a distribution alignment operation is employed to impose the cluster probability distribution of strong-augmented instances close to those of weak-augmented instances, to reduce the possibility of generating incorrect pseudo-labels at the initial training phase. Extensive comparisons experiments are conducted and the results illustrate that PCDAC is superior to the SOTA methods. The code is available on GitHub at https://github.com/LiuZiweiAI/PCDAC . Graphical abstract: Image, graphical abstract