Latent Domain Learning with Dynamic Residual Adapters

Understand

A practical shortcoming of deep neural networks is their specialization to a single task and domain.

• While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success relies on the presence of domain labels, typically requiring manual annotation and careful curation of datasets.
• Here we focus on a less explored, but more realistic case: learning from data from multiple domains, without access to domain annotations.
• In this scenario, standard model training leads to the overfitting of large domains, while disregarding smaller ones.