HCSC: Hierarchical Contrastive Selective Coding

Autor: Guo, Yuanfan, Xu, Minghao, Li, Jiawen, Ni, Bingbing, Zhu, Xuanyu, Sun, Zhenbang, Xu, Yi
Rok vydání: 2022
Předmět:
Druh dokumentu: Working Paper
Popis: Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coarser-grained semantics. Capturing such structures with image representations can greatly benefit the semantic understanding on various downstream tasks. Existing contrastive representation learning methods lack such an important model capability. In addition, the negative pairs used in these methods are not guaranteed to be semantically distinct, which could further hamper the structural correctness of learned image representations. To tackle these limitations, we propose a novel contrastive learning framework called Hierarchical Contrastive Selective Coding (HCSC). In this framework, a set of hierarchical prototypes are constructed and also dynamically updated to represent the hierarchical semantic structures underlying the data in the latent space. To make image representations better fit such semantic structures, we employ and further improve conventional instance-wise and prototypical contrastive learning via an elaborate pair selection scheme. This scheme seeks to select more diverse positive pairs with similar semantics and more precise negative pairs with truly distinct semantics. On extensive downstream tasks, we verify the superior performance of HCSC over state-of-the-art contrastive methods, and the effectiveness of major model components is proved by plentiful analytical studies. We build a comprehensive model zoo in Sec. D. Our source code and model weights are available at https://github.com/gyfastas/HCSC
Comment: Accepted by CVPR 2022. arXiv v3: 800 epoch multi-crop model released; arXiv v2: more model weights released; arXiv v1: code & model weights released
Databáze: arXiv