NeurIPS 2020spotlight162 citations

A causal view of compositional zero-shot recognition

Yuval Atzmon, Felix Kreuk, Uri Shalit, Gal Chechik

Abstract

People easily recognize new visual categories that are new combinations of known components. This compositional generalization capacity is critical for learning in real-world domains like vision and language because the long tail of new combinations dominates the distribution. Unfortunately, learning systems struggle with compositional generalization because they often build on features that are correlated with class labels even if they are not "essential" for the class. This leads to consistent misclassification of samples from a new distribution, like new combinations of known components.

BibTeX
@inproceedings{NEURIPS2020_1010cedf,
 author = {Atzmon, Yuval and Kreuk, Felix and Shalit, Uri and Chechik, Gal},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {1462--1473},
 publisher = {Curran Associates, Inc.},
 title = {A causal view of compositional zero-shot recognition},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/1010cedf85f6a7e24b087e63235dc12e-Paper.pdf},
 volume = {33},
 year = {2020}
}
A causal view of compositional zero-shot recognition · NeurIPS 2020