Class is invariant to context and vice versa: On learning invariance for out-of-distribution generalization
Out-Of-Distribution generalization (OOD) is all about learning invariance against environmental changes. If the context in every class is evenly distributed, OOD would be trivial because the context can be easily removed due to an underlying principle: class is invariant to context. However, collect...
Saved in:
Main Authors: | QI, Jiaxin, TANG, Kaihua, SUN, Qianru, HUA, Xian-Sheng, ZHANG, Hanwang |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7514 https://ink.library.smu.edu.sg/context/sis_research/article/8517/viewcontent/ECCV2022__Class_Is_Invariant_to_Context_and_Vice_Versa__On_Learning_Invariance_forOut_Of_Distribution_Generalization__Camera_Ready__.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Equivariance and invariance inductive bias for learning from insufficient data
by: WANG, Tan, et al.
Published: (2022) -
13 questions: Using imagination to stimulate writing (and vice-versa)
by: Wright, Ma. Teresa H.
Published: (1998) -
From dual pairs of Gabor frames to dual pairs of wavelet frames and vice versa
by: Christensen, O., et al.
Published: (2014) -
The mudskipper Periophthalmodon schlosseri respires more efficiently on land than in water and vice versa for Boleophthalmus boddaerti
by: Kok, W.K., et al.
Published: (2014) -
Make the U in UDA matter: Invariant consistency learning for unsupervised domain adaptation
by: YUE, Zhongqi, et al.
Published: (2023)