Search Results for author:
Found 4 papers, 3 papers with code
Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
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.
Invariant Feature Learning for Generalized Long-Tailed Classification
In fact, even if the class is balanced, samples within each class may still be long-tailed due to the varying attributes.
Ranked #1 on
Long-tail Learning
on ImageNet-GLT
Deconfounded Visual Grounding
We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck.
Two Causal Principles for Improving Visual Dialog
This paper unravels the design tricks adopted by us, the champion team MReaL-BDAI, for Visual Dialog Challenge 2019: two causal principles for improving Visual Dialog (VisDial).
