Can contrastive learning avoid shortcut solutions?

Can contrastive learning avoid shortcut solutions?

21 June 2021

Joshua Robinson

Kayhan Batmanghelich

Stefanie Jegelka

Papers citing "Can contrastive learning avoid shortcut solutions?"

8 / 58 papers shown

Title
Robustness May Be at Odds with Accuracy Dimitris Tsipras Shibani Santurkar Logan Engstrom Alexander Turner Aleksander Madry AAML 62 1,772 0 30 May 2018
The Implicit Bias of Gradient Descent on Separable Data Daniel Soudry Elad Hoffer Mor Shpigel Nacson Suriya Gunasekar Nathan Srebro 55 908 0 27 Oct 2017
mixup: Beyond Empirical Risk Minimization Hongyi Zhang Moustapha Cissé Yann N. Dauphin David Lopez-Paz NoLa 221 9,687 0 25 Oct 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 201 11,962 0 19 Jun 2017
Context Encoders: Feature Learning by Inpainting Deepak Pathak Philipp Krahenbuhl Jeff Donahue Trevor Darrell Alexei A. Efros SSL 29 5,277 0 25 Apr 2016
Colorful Image Colorization Richard Y. Zhang Phillip Isola Alexei A. Efros 99 3,524 0 28 Mar 2016
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 143 18,922 0 20 Dec 2014
Intriguing properties of neural networks Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna D. Erhan Ian Goodfellow Rob Fergus AAML 140 14,831 1 21 Dec 2013