Prototypical contrastive learning of unsupervised representations
This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that bridges contrastive learning with clustering. PCL not only learns low-level features for the task of instance discrimination, but more importantly, it encodes semantic structures discover...
Saved in:
Main Authors: | LI, Junnan, ZHOU, Pan, XIONG, Caiming, HOI, Steven C. H. |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8993 https://ink.library.smu.edu.sg/context/sis_research/article/9996/viewcontent/2021_ICLR_PCL.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
A theory-driven self-labeling refinement method for contrastive representation learning
by: ZHOU, Pan, et al.
Published: (2021) -
Exploring diffusion time-steps for unsupervised representation learning
by: YUE, Zhongqi, et al.
Published: (2024) -
Prototypical graph contrastive learning
by: LIN, Shuai, et al.
Published: (2022) -
Transporting causal mechanisms for unsupervised domain adaptation
by: YUE, Zhongqi, et al.
Published: (2021) -
Improving tail-class representation with centroid contrastive learning
by: Tiong, Anthony Meng Huat, et al.
Published: (2023)