English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse
  1. View item / 
  2. Item Summary

Item

ITEM ACTIONSEXPORT
Add to Basket
  DetailsSummary

Released
Conference Paper

CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning

MPS-Authors
/persons/resource/persons242093

Fan,  Yue
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons261420

Dai,  Dengxin
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons45383

Schiele,  Bernt
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
Supplementary Material (public)
There is no public supplementary material available
Citation

Fan, Y., Dai, D., & Schiele, B. (2022). CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 14554-14564). Piscataway, NJ: IEEE. doi:10.1109/CVPR52688.2022.01417.


Cite as: https://hdl.handle.net/21.11116/0000-000A-16BA-C
Abstract
In this paper, we propose a novel co-learning framework (CoSSL) with
decoupled representation learning and classifier learning for imbalanced SSL.
To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE)
for classifier learning. Furthermore, the current evaluation protocol for
imbalanced SSL focuses only on balanced test sets, which has limited
practicality in real-world scenarios. Therefore, we further conduct a
comprehensive evaluation under various shifted test distributions. In
experiments, we show that our approach outperforms other methods over a large
range of shifted distributions, achieving state-of-the-art performance on
benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our
code will be made publicly available.