IEEE Computational Intelligence Magazine - August 2022 - 11

Yongduan Song, Chongqing University, CHINA
Jon Garibaldi, University of Nottingham, UK
Carlos A. Coello Coello, CINVESTAV-IPN, MEXICO
Georgios N. Yannakakis, University of Malta, MALTA
Huajin Tang, Zhejiang University, CHINA
Yew Soon Ong, Nanyang Technological University, SINGAPORE
Hussein Abbass, University of New South Wales, AUSTRALIA
Spotlight
Publication
CIS Publication Spotlight
IEEE Transactions on Neural
Networks and Learning Systems
A Review of Single-Source Deep Unsupervised
Visual Domain Adaptation, by
S. Zhao, X. Yue, S. Zhang, B. Li, H.
Zhao, B. Wu, R. Krishna, J. E. Gonzalez,
A. L. Sangiovanni-Vincentelli, S.
A. Seshia, and K. Keutzer, IEEE
Transactions on Neural Networks and
Learning Systems, Vol. 33, No. 2, Feb
2022, pp. 473-493.
Digital Object Identifier: 10.1109/
TNNLS.2020.3028503
" Large-scale labeled training datasets
have enabled deep neural networks to
excel across a wide range of benchmark
vision tasks. However, in many applications,
it is prohibitively expensive and
time-consuming to obtain large quantities
of labeled data. To cope with limited
labeled training data, many have attempted
to directly apply models trained on a
largescale labeled source domain to
another sparsely labeled or unlabeled target
domain. Unfortunately, direct transfer
across domains often performs poorly
due to the presence of domain shift or
dataset bias. Domain adaptation (DA) is a
machine learning paradigm that aims to
learn a model from a source domain that
can perform well on a different (but
related) target domain. In this article, we
review the latest single-source deep
unsupervised DA methods focused on
visual tasks and discuss new perspectives
for future research. We begin with the
Digital Object Identifier 10.1109/MCI.2022.3180882
Date of current version: 19 July 2022
definitions of different DA strategies and
the descriptions of existing benchmark
datasets. We then summarize and compare
different categories of single-source
unsupervised DA methods, including
discrepancy-based methods, adversarial
discriminative methods, adversarial generative
methods, and self-supervision
based methods. Finally, we discuss future
research directions with challenges and
possible solutions. "
IEEE Transactions on
Fuzzy Systems
Variational Fuzzy Superpixel Segmentation,
by T. C. Ng and S. K. Choy,
IEEE Transactions on Fuzzy Systems,
Vol. 30, No. 1, Jan 2022, pp. 14-26.
Digital Object Identifier: 10.1109/
TFUZZ.2020.3029939
" This article presents a novel variational
model based on fuzzy clustering
and total variation regularization for
superpixel segmentation. Compared
with the classical hard-labeled methodologies,
our approach gives soft results
via the fuzzy membership function, and
moreover, the use of total variation provides
additional information that can
enhance the superpixel regularity, which
in turn improves the segmentation performance.
To efficiently minimize the
energy functional of the proposed model,
we adopt an alternating direction method
of multipliers with the modified
Chambolle's fast duality projection algorithm.
Our algorithm can generate regular
and compact superpixels with high
segmentation accuracy, satisfactory
boundary adherence, and low computational
cost. Comparative experimental
results with the current state-of-the-art
approaches reveal the superior performance
of the proposed method. "
How to Vary the Input Space of a T-S
Fuzzy Model: A TP Model Transformation-Based
Approach, by P. Baranyi, IEEE
Transactions on Fuzzy Systems, Vol. 30,
No. 2, Feb 2022, pp. 345-356.
Digital Object Identifier: 10.1109/
TFUZZ.2020.3038488
" The motivation behind 15 years of
continuous development within the
topic of the tensor product (TP) model
transformation is that the greater the
number of parameters or components
of the Takagi-Sugeno (T-S) fuzzy
model one can manipulate, the larger
complexity reduction or control optimization
one can achieve. This article proposes
a radically new type of extension
to the TP model transformation. While
earlier variants of the TP model transformation
focused on how the antecedent-consequent
fuzzy set system of a
AUGUST 2022 | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 11
©SHUTTERSTOCK.COM/HERMIN
http://www.SHUTTERSTOCK.COM/HERMIN
IEEE Computational Intelligence Magazine - August 2022

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - August 2022
