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

researchr

You are not signed in
Sign in
Sign up

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]

This author has not been identified. Look up 'Michael Zhang' in GoogleThis author has not been identified. Look up 'Nimit Sharad Sohoni' in GoogleThis author has not been identified. Look up 'Hongyang R. Zhang' in GoogleThis author has not been identified. Look up 'Chelsea Finn' in GoogleThis author has not been identified. Look up 'Christopher Ré' in Google

runs on WebDSL