Boosting Domain Adaptation by Discovering Latent Domains

TL;DR

This paper proposes a CNN-based method that automatically discovers latent domains within datasets and uses this information to improve domain adaptation performance, especially when domain labels are unavailable.

Contribution

It introduces a novel CNN architecture with components for automatic latent domain discovery and distribution alignment, enhancing multi-source domain adaptation.

Findings

Outperforms state-of-the-art multi-source DA methods

Automatically discovers latent domains without manual labels

Improves robustness of target classifiers

Abstract

Current Domain Adaptation (DA) methods based on deep architectures assume that the source samples arise from a single distribution. However, in practice, most datasets can be regarded as mixtures of multiple domains. In these cases exploiting single-source DA methods for learning target classifiers may lead to sub-optimal, if not poor, results. In addition, in many applications it is difficult to manually provide the domain labels for all source data points, i.e. latent domains should be automatically discovered. This paper introduces a novel Convolutional Neural Network (CNN) architecture which (i) automatically discovers latent domains in visual datasets and (ii) exploits this information to learn robust target classifiers. Our approach is based on the introduction of two main components, which can be embedded into any existing CNN architecture: (i) a side branch that automatically computes the assignment of a source sample to a latent domain and (ii) novel layers that exploit domain membership information to appropriately align the distribution of the CNN internal feature representations to a reference distribution. We test our approach on publicly-available datasets, showing that it outperforms state-of-the-art multi-source DA methods by a large margin.