A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
Learning robust models that generalize well under changes in the data distribution is critical for real-world applications. To this end, there has been a growing surge of interest to learn simultaneously from multiple training domains - while enforcing different types of invariance across those domains. Yet, all existing approaches fail to show systematic benefits under controlled evaluation protocols. In this paper, we introduce a new regularization - named Fishr - that enforces domainarXiv:2109.02934v3 fatcat:kvujruuh3jgvrc3ik76xvezv4e