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 convnet 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.
Boosting binary masks for multi-domain learning through affine transformations / Mancini, M.; Ricci, E.; Caputo, B.; RotaBulo, S.. - In: MACHINE VISION AND APPLICATIONS. - ISSN 0932-8092. - 31:6(2020).
Scheda prodotto non validato
I dati visualizzati non sono stati ancora sottoposti a validazione formale da parte dello Staff di IRIS, ma sono stati ugualmente trasmessi al Sito Docente Cineca (Loginmiur).
Titolo: | Boosting binary masks for multi-domain learning through affine transformations | |
Autori: | Mancini, M.; Ricci, E.; Caputo, B.; RotaBulo, S. | |
Autori Unitn: | ||
Titolo del periodico: | MACHINE VISION AND APPLICATIONS | |
Anno di pubblicazione: | 2020 | |
Numero e parte del fascicolo: | 6 | |
Codice identificativo Scopus: | 2-s2.0-85087046274 | |
Codice identificativo WOS: | WOS:000542826800001 | |
Digital Object Identifier (DOI): | http://dx.doi.org/10.1007/s00138-020-01090-5 | |
Handle: | http://hdl.handle.net/11572/284402 | |
Citazione: | Boosting binary masks for multi-domain learning through affine transformations / Mancini, M.; Ricci, E.; Caputo, B.; RotaBulo, S.. - In: MACHINE VISION AND APPLICATIONS. - ISSN 0932-8092. - 31:6(2020). | |
Appare nelle tipologie: |