.png){kind=icon}
.png){kind=icon}
Return
Contrastive visual clustering for improving instance-level contrastive learning as a plugin
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2024.110631.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Contrastive learning has achieved remarkable success in computer vision, however it is built on instancelevel discrimination which leaves the valuable intra-class correlation in dataset unexploited. Current semantic clustering methods are proven to be helpful but they would suffer from the error accumulated in the iteration process without ground -truth guidance. In an attempt to remedy the clustering error accumulation when utilizing intra-class correlation for contrastive learning, we propose an online Contrastive Visual Clustering (CVC) method with two actions: gathering instances with highly similar feature embeddings, and penalizing instances being clustered with low confidence. CVC can integrate with not only contrastive learning but also arbitrary self -supervised learning frameworks simply as a plugin. Under various experiment settings, we show that CVC improves the linear classification performance by a large margin for models pre -trained with self -supervised representation learning, in both image and video scenarios. The code is available at https://github.com/yliu1229/CVC.
Keywords:
Self-supervised learning
Contrastive learning
Deep clustering
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.