AutoDIAL: Automatic DomaIn Alignment Layers

Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulo; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 5067-5075


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.

Related Material

[pdf] [Supp] [arXiv]
author = {Maria Carlucci, Fabio and Porzi, Lorenzo and Caputo, Barbara and Ricci, Elisa and Rota Bulo, Samuel},
title = {AutoDIAL: Automatic DomaIn Alignment Layers},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}