Domain Generalization (PACS)

This is the track of the state-of-the-art methods on PACS benchmark.

Domain generalization (DG) assumes a model is trained from multiple observed domains while it is expected to perform well on any unseen domains. PACS consists of Art painting, Cartoon, Photo and Sketch domains, which so far considers the largest domain shift as it is from the different image style depictions.

Dataset

Name Year Domains Images Classes
PACS 2017 4 9991 7

Benchmarks

Base Model Methods Venue Art painting Cartoon Photo Sketch Ave
AlexNet [1] ICCV'17 62.86 66.97 89.50 57.51 69.21
AlexNet [2] AAAI'18 66.23 66.88 88.00 58.96 70.01
AlexNet [3] ICIP'18 64.1 66.8 90.2 60.1 70.3
AlexNet [4] NeurIPS'18 69.82 70.35 91.07 59.26 72.62
AlexNet [5] ICLR'19 66.8 69.7 87.9 56.3 70.2
AlexNet [6] CVPR'19 67.63 71.71 89.00 65.18 73.38
AlexNet [7] preprint 61.2 63.8 82.9 59.0 66.7

References

[1] Da Li, Yongxin Yang, Yi-Zhe Song, and Timothy M Hospedales. Deeper, broader and artier domain generalization. In ICCV, 2017.

[2] Da Li, Yongxin Yang, Yi-Zhe Song, and Timothy M Hospedales. Learning to generalize: Meta-learning for domain generalization. In AAAI, 2018.

[3] Massimiliano Mancini, Samuel Rota Bulo`, Barbara Caputo, Elisa Ricci. Best sources forward: domain generalization through source-specific nets. In ICIP, 2018.

[4] Yogesh Balaji, Swami Sankaranarayanan and Rama Chellappa. MetaReg: Towards Domain Generalization using Meta-Regularization. In NeurIPS, 2018.

[5] Haohan Wang, Zexue He, Zachary C. Lipton and Eric P. Xing. Learning Robust Representations by Projecting Superficial Statistics Out. In ICLR, 2019.

[6] Fabio Maria Carlucci, Antonio D'Innocente, Silvia Bucci, Barbara Caputo, Tatiana Tommasi. Domain Generalization by Solving Jigsaw Puzzles. In CVPR, 2019.

[7] Kei Akuzawa, Yusuke Iwasawa and Yutaka Matsuo. Domain Generalization via Invariant Representation under Domain-Class Dependency. preprint, 2019.

Maintainers

Da Li and Yongxin Yang