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 performe d, 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.
AutoDIAL: Automatic Domain Alignment Layers / Cariucci, Fabio Maria; Porzi, Lorenzo; Caputo, Barbara; Ricci, Elisa; Bulo, Samuel Rota. - ELETTRONICO. - (2017), pp. 5077-5085. ((Intervento presentato al convegno ICCV tenutosi a Venice, Italy nel 22-29 October 2017.
Titolo: | AutoDIAL: Automatic Domain Alignment Layers | |
Autori: | Cariucci, Fabio Maria; Porzi, Lorenzo; Caputo, Barbara; Ricci, Elisa; Bulo, Samuel Rota | |
Autori Unitn: | ||
Titolo del volume contenente il saggio: | IEEE International Conference on Computer Vision (ICCV) | |
Luogo di edizione: | Piscataway, New Jersey, US | |
Casa editrice: | IEEE | |
Anno di pubblicazione: | 2017 | |
Codice identificativo Scopus: | 2-s2.0-85041904158 | |
Codice identificativo WOS: | WOS:000425498405017 | |
ISBN: | 978-1-5386-1032-9 | |
Handle: | http://hdl.handle.net/11572/194340 | |
Citazione: | AutoDIAL: Automatic Domain Alignment Layers / Cariucci, Fabio Maria; Porzi, Lorenzo; Caputo, Barbara; Ricci, Elisa; Bulo, Samuel Rota. - ELETTRONICO. - (2017), pp. 5077-5085. ((Intervento presentato al convegno ICCV tenutosi a Venice, Italy nel 22-29 October 2017. | |
Appare nelle tipologie: | 04.1 Saggio in atti di convegno (Paper in proceedings) |
File in questo prodotto:
File | Descrizione | Tipologia | Licenza | |
---|---|---|---|---|
08237804.pdf | Versione editoriale (Publisher’s layout) | Tutti i diritti riservati (All rights reserved) | Administrator |