@InProceedings{CavallariRibePont:2018:DoCrFe,
author = "Cavallari, Gabriel B. and Ribeiro, Leonardo S. F. and Ponti,
Moacir A.",
affiliation = "USP and USP and USP",
title = "Unsupervised representation learning using convolutional and
stacked auto-encoders: a domain and cross-domain feature space
analysis",
booktitle = "Proceedings...",
year = "2018",
editor = "Ross, Arun and Gastal, Eduardo S. L. and Jorge, Joaquim A. and
Queiroz, Ricardo L. de and Minetto, Rodrigo and Sarkar, Sudeep and
Papa, Jo{\~a}o Paulo and Oliveira, Manuel M. and Arbel{\'a}ez,
Pablo and Mery, Domingo and Oliveira, Maria Cristina Ferreira de
and Spina, Thiago Vallin and Mendes, Caroline Mazetto and Costa,
Henrique S{\'e}rgio Gutierrez and Mejail, Marta Estela and Geus,
Klaus de and Scheer, Sergio",
organization = "Conference on Graphics, Patterns and Images, 31. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "Deep Learning, Representation learning, Feature extraction,
Unsupervised feature learning.",
abstract = "A feature learning task involves training models that are capable
of inferring good representations (transformations of the original
space) from input data alone. When working with limited or
unlabelled data, and also when multiple visual domains are
considered, methods that rely on large annotated datasets, such as
Convolutional Neural Networks (CNNs), cannot be employed. In this
paper we investigate different auto-encoder (AE) architectures,
which require no labels, and explore training strategies to learn
representations from images. The models are evaluated considering
both the reconstruction error of the images and the feature spaces
in terms of their discriminative power. We study the role of dense
and convolutional layers on the results, as well as the depth and
capacity of the networks, since those are shown to affect both the
dimensionality reduction and the capability of generalising for
different visual domains. Classification results with AE features
were as discriminative as pre-trained CNN features. Our findings
can be used as guidelines for the design of unsupervised
representation learning methods within and across domains.",
conference-location = "Foz do Igua{\c{c}}u, PR, Brazil",
conference-year = "29 Oct.-1 Nov. 2018",
doi = "10.1109/SIBGRAPI.2018.00063",
url = "http://dx.doi.org/10.1109/SIBGRAPI.2018.00063",
language = "en",
ibi = "8JMKD3MGPAW/3RN5TEE",
url = "http://urlib.net/ibi/8JMKD3MGPAW/3RN5TEE",
targetfile = "sibgrapi-2018_Analysis_of_cross_domain_unsupervised_learning.pdf",
urlaccessdate = "2024, May 01"
}