1. Invariance principle meets information bottleneck for out-of-distribution generalization;Ahuja;Adv. Neural Inf. Process. Syst.,2021
2. Invariant risk minimization;Arjovsky,2019
3. A theory of learning from different domains;Ben-David;Mach. Learn.,2010
4. Domain-adversarial training of neural networks;Ganin;J. Mach. Learn. Res.,2016
5. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness;Geirhos,2019