Request to add Test-Time Training approaches for Out-of-Domain Generalization

[syguan96]

Hi, thanks for your efforts to maintain this comprehensive repository!

I recommend collecting Test-Time Training approaches to category Out-of-Domain Generalization. Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time. Here are some suggested papers:

Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt
ICML 2020
[Code] [Paper]

Tent: Fully Test-Time Adaptation by Entropy Minimization
Wang Dequan, Shelhamer Evan, Liu Shaoteng, Olshausen Bruno, Darrell Trevor
ICLR 2021
[Code] Paper]

Test-Time Training with Masked Autoencoders
Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei A. Efros
NeurIPS 2022
[Code] [Paper]

Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation
Shanyan Guan, Jingwei Xu, Michelle Z. He, Yunbo Wang, Bingbing Ni, Xiaokang Yang
TPAMI 2022
[Code] [Paper]