AutoDIAL: Automatic DomaIn Alignment Layers
This addresses domain adaptation for machine learning models, offering an automated approach to improve generalization across different data settings, though it appears incremental in method.
The paper tackles the problem of domain shift in classifiers by automatically learning the degree of feature alignment needed at different network layers, achieving strong performance on public benchmarks in unsupervised settings.
Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains. Attempts to align them have traditionally resulted in works reducing the domain shift by introducing appropriate loss terms, measuring the discrepancies between source and target distributions, in the objective function. Here we take a different route, proposing to align the learned representations by embedding in any given network specific Domain Alignment Layers, designed to match the source and target feature distributions to a reference one. Opposite to previous works which define a priori in which layers adaptation should be performed, our method is able to automatically learn the degree of feature alignment required at different levels of the deep network. Thorough experiments on different public benchmarks, in the unsupervised setting, confirm the power of our approach.