Boosting binary masks for multi-domain learning through affine transformations

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...

Full description

Saved in:
Bibliographic Details
Published in:Machine vision and applications 2020-09, Vol.31 (6), Article 42
Main Authors: Mancini, Massimiliano, Ricci, Elisa, Caputo, Barbara, Rota Bulò, Samuel
Format: Article
Language:English
Subjects:
Affine transformations
Algorithms
Communications Engineering
Computer Science
Image Processing and Computer Vision
Machine learning
Masking
Masks
Mathematical models
Networks
Original Paper
Parameters
Pattern Recognition
Vision systems
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0932-8092
1432-1769
DOI:10.1007/s00138-020-01090-5