AutoDIAL: Automatic Domain Alignment Layers
Authors:
- Fabio Maria CarlucciFCFabio Maria Carlucci
- Lorenzo PorziLPLorenzo Porzi
- Barbara CaputoBCBarbara Caputo
- Elisa RicciERElisa Ricci
- Samuel Rota BuloSBSamuel Rota Bulo
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5077-5085
Abstract
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 performed, 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.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation2017
- Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation2016
- Simultaneous Deep Transfer Across Domains and Tasks2015
- Deep Learning of Scene-Specific Classifier for Pedestrian Detection2014
- Unsupervised Visual Domain Adaptation Using Subspace Alignment2013
- Selective Transfer Machine for Personalized Facial Action Unit Detection2013
- Transfer Sparse Coding for Robust Image Representation2013
- No Bias Left behind: Covariate Shift Adaptation for Discriminative 3D Pose Estimation2012
- Domain Adaptation via Transfer Component AnalysisIEEE Transactions on Neural Networks, 2010
- Normal Discrimination with Unclassified ObservationsJournal of the American Statistical Association, 1978