A theory-driven self-labeling refinement method for contrastive representation learning
For an image query, unsupervised contrastive learning labels crops of the same image as positives, and other image crops as negatives. Although intuitive, such a native label assignment strategy cannot reveal the underlying semantic similarity between a query and its positives and negatives, and imp...
Saved in:
Main Authors: | ZHOU, Pan, XIONG, Caiming, YUAN, Xiao-Tong |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8989 https://ink.library.smu.edu.sg/context/sis_research/article/9992/viewcontent/2021_NeurIPS_SANE.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Prototypical contrastive learning of unsupervised representations
by: LI, Junnan, et al.
Published: (2021) -
Systems and methods for contrastive learning with self-labeling refinement
by: ZHOU, Pan, et al.
Published: (2022) -
Faster first-order methods for stochastic non-convex optimization on Riemannian manifolds
by: ZHOU, Pan, et al.
Published: (2019) -
Efficient meta learning via minibatch proximal update
by: ZHOU, Pan, et al.
Published: (2019) -
Self-supervised learning disentangled group representation as feature
by: WANG, Tan, et al.
Published: (2021)