@InProceedings{SilvaPedFarPapAlm:2021:ImTrDo,
author = "Silva, Lucas Fernando Alvarenga e and Pedronette, Daniel Carlos
Guimar{\~a}es and Faria, Fabio Augusto and Papa, Jo{\~a}o Paulo
and Almeida, Jurandy",
affiliation = "{Universidade Federal de S{\~a}o Paulo } and {S{\~a}o Paulo
State University } and {Universidade Federal de S{\~a}o Paulo }
and {S{\~a}o Paulo State University } and {Universidade Federal
de S{\~a}o Paulo}",
title = "Improving Transferability of Domain Adaptation Networks Through
Domain Alignment Layers",
booktitle = "Proceedings...",
year = "2021",
editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and
Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario
and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos,
Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira,
Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir
A. and Fernandes, Leandro A. F. and Avila, Sandra",
organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "deep learning, unsupervised domain adaptation, image
recognition.",
abstract = "Deep learning (DL) has been the primary approach used in various
computer vision tasks due to its relevant results achieved on many
tasks. However, on real-world scenarios with partially or no
labeled data, DL methods are also prone to the well-known domain
shift problem. Multi-source unsupervised domain adaptation (MSDA)
aims at learning a predictor for an unlabeled domain by assigning
weak knowledge from a bag of source models. However, most works
conduct domain adaptation leveraging only the extracted features
and reducing their domain shift from the perspective of loss
function designs. In this paper, we argue that it is not
sufficient to handle domain shift only based on domain-level
features, but it is also essential to align such information on
the feature space. Unlike previous works, we focus on the network
design and propose to embed Multi-Source version of DomaIn
Alignment Layers (MS-DIAL) at different levels of the predictor.
These layers are designed to match the feature distributions
between different domains and can be easily applied to various
MSDA methods. To show the robustness of our approach, we conducted
an extensive experimental evaluation considering two challenging
scenarios: digit recognition and object classification. The
experimental results indicated that our approach can improve
state-of-the-art MSDA methods, yielding relative gains of up to
+30.64% on their classification accuracies.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
doi = "10.1109/SIBGRAPI54419.2021.00031",
url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00031",
language = "en",
ibi = "8JMKD3MGPEW34M/45CPUQ2",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CPUQ2",
targetfile = "sibgrapi95.pdf",
urlaccessdate = "2024, May 06"
}