Reducing Implicit Bias in Latent Domain Learning

Lucas Deecke, Timothy Hospedales, Hakan Bilen

Keywords: Latent Domain Learning, CNN Architectures

Abstract: A fundamental shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in multi-domain learning enable the learning of more domain-agnostic features, their success relies firmly on the presence of domain labels, typically requiring manual annotation and careful curation of datasets. Here we focus on latent domain learning, a highly realistic, yet less explored scenario: learning from data from different domains, without access to domain annotations. This is a particularly challenging problem, since standard models exhibit an implicit bias toward learning only the large domains in data, while disregarding smaller ones. To address this issue, we propose dynamic residual adapters that adaptively account for latent domains, and weighted domain transfer – a novel augmentation strategy designed specifically for this setting. Our techniques are evaluated on image classification tasks containing multiple unannotated domains, and we demonstrate they enhance performance, in particular, on the smallest of these.

One-sentence Summary: We demonstrate that standard models suppress underrepresented latent domains, and formulate novel strategies to limit this behavior.

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

Reviewed Version (pdf): https://openreview.net/references/pdf?id=iqOQ7bIUbc