The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and target domains. Alleviating the domain shift problem, especially in the challenging setting where no labeled data are available for the target domain, is paramount for having visual recognition systems working in the wild. As the problem stems from a shift among distributions, intuitively one should try to align them. In the literature, this has resulted in a stream of works attempting to align the feature representations learned from the source and target domains. Here we take a different route. Rather than introducing regularization terms aiming to promote the alignment of the two representations, we act at the distribution level through the introduction of \emphDomaIn Alignment Layers (\DIAL), able to match the observed source and target data distributions to a reference one. Thorough experiments on three different public benchmarks we confirm the power of our approach.
Dettaglio pubblicazione
2017, ICIAP: International Conference on Image Analysis and Processing, Pages 87-100 (volume: 1)
Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation (04b Atto di convegno in volume)
Carlucci FABIO MARIA, Porzi Lorenzo, Caputo Barbara, Ricci Elisa, ROTA BULO' Samuel
ISBN: 978-3-319-68559-5
keywords