1 code implementation • ICCV 2023 • Sriram Yenamandra, Pratik Ramesh, Viraj Prabhu, Judy Hoffman
Computer vision datasets frequently contain spurious correlations between task-relevant labels and (easy to learn) latent task-irrelevant attributes (e. g. context).
1 code implementation • 4 May 2023 • George Stoica, Daniel Bolya, Jakob Bjorner, Pratik Ramesh, Taylor Hearn, Judy Hoffman
While this works for models trained on the same task, we find that this fails to account for the differences in models trained on disjoint tasks.