@InProceedings{JordãoSchw:2021:DeSpOd,
author = "Jord{\~a}o, Artur and Schwartz, William Robson",
affiliation = "{Federal University of Minas Gerais} and {Federal University of
Minas Gerais}",
title = "Partial Least Squares: A Deep Space Odyssey",
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 = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
address = "Porto Alegre",
keywords = "Computing, computer vision, estimation theory, pattern
recognition.",
abstract = "Modern visual pattern recognition models are based on deep
convolutional networks. Such models are computationally expensive,
hindering applicability on resource-constrained devices. To handle
this problem, we propose three strategies. The first removes
unimportant structures (neurons or layers) of convolutional
networks, reducing their computational cost. The second inserts
structures to design architectures automatically, enabling us to
build high-performance networks. The third combines multiple
layers of convolutional networks, enhancing data representation at
negligible additional cost. These strategies are based on Partial
Least Squares (PLS) which, despite promising results, is
infeasible on large datasets due to memory constraints. To address
this issue, we also propose a discriminative and low-complexity
incremental PLS that learns a compact representation of the data
using a single sample at a time, thus enabling applicability on
large datasets. We assess the effectiveness of our approaches on
several convolutional architectures and computer vision tasks,
which include image classification, face verification and activity
recognition. Our approaches reduce the resource overhead of both
convolutional networks and Partial Least Squares, promoting
energy- and hardware-friendly models for the academy and industry
scenarios. Compared to state-of-the-art methods for the same
purpose, we obtain one of the best trade-offs between predictive
ability and computational cost.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
language = "en",
ibi = "8JMKD3MGPEW34M/45CTEAE",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CTEAE",
targetfile = "Article.pdf",
urlaccessdate = "2024, May 06"
}