Reviewed Version (pdf): https://openreview.net/references/pdf?id=jvBofsVTR3
Keywords: Conditional Computation, Generalization
Abstract: In this work we tackle the problem of out-of-distribution generalization through conditional computation. Real-world applications often exhibit a larger distributional shift between training and test data than most datasets used in research. On the other hand, training data in such applications often comes with additional annotation. We propose a method for leveraging this extra information by using an auxiliary network that modulates activations of the main network. We show that this approach improves performance over a strong baseline on the Inria Aerial Image Labeling and the Tumor-Infiltrating Lymphocytes (TIL) Datasets, which by design evaluate out-of-distribution generalization in both semantic segmentation and image classification.
One-sentence Summary: We propose a framework for improving out of distribution (OOD) generalization by leveraging auxiliary data via conditional normalization.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics