Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
This addresses the problem of efficiently adapting neural networks to multiple domains for researchers and practitioners in computer vision, though it is incremental over existing binary mask approaches.
The paper tackles multi-domain learning by proposing a method using affine transformations of binary masks to adapt a single model to multiple visual domains sequentially, achieving performance close to domain-specific models with just over 1 bit per parameter per domain.
In this work, we present a new, algorithm for multi-domain learning. Given a pretrained architecture and a set of visual domains received sequentially, the goal of multi-domain learning is to produce a single model performing a task in all the domains together. Recent works showed how we can address this problem by masking the internal weights of a given original conv-net through learned binary variables. In this work, we provide a general formulation of binary mask based models for multi-domain learning by affine transformations of the original network parameters. Our formulation obtains significantly higher levels of adaptation to new domains, achieving performances comparable to domain-specific models while requiring slightly more than 1 bit per network parameter per additional domain. Experiments on two popular benchmarks showcase the power of our approach, achieving performances close to state-of-the-art methods on the Visual Decathlon Challenge.