Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations

Michael Zhang, Nimit Sharad Sohoni, Hongyang R. Zhang, Chelsea Finn, Christopher Ré. Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu 0001, Sivan Sabato, editors, International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA. Volume 162 of Proceedings of Machine Learning Research, pages 26484-26516, PMLR, 2022. [doi]

@inproceedings{ZhangSZFR22,
  title = {Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations},
  author = {Michael Zhang and Nimit Sharad Sohoni and Hongyang R. Zhang and Chelsea Finn and Christopher Ré},
  year = {2022},
  url = {https://proceedings.mlr.press/v162/zhang22z.html},
  researchr = {https://researchr.org/publication/ZhangSZFR22},
  cites = {0},
  citedby = {0},
  pages = {26484-26516},
  booktitle = {International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA},
  editor = {Kamalika Chaudhuri and Stefanie Jegelka and Le Song and Csaba Szepesvári and Gang Niu 0001 and Sivan Sabato},
  volume = {162},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
}