Zobrazeno 1 - 10
of 96
pro vyhledávání: '"Alessandro L. Koerich"'
Autor:
Thiago M. Paixão, Rodrigo F. Berriel, Maria C.S. Boeres, Alessandro L. Koerich, Claudine Badue, Alberto F. De Souza, Thiago Oliveira-Santos
Publikováno v:
Pattern Recognition Letters. 164:1-8
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a4118c623f22c562a19e34231a92797e
https://doi.org/10.1016/j.patrec.2022.10.011
https://doi.org/10.1016/j.patrec.2022.10.011
Publikováno v:
Neurocomputing. 467:427-441
Automatic plant classification is challenging due to the vast biodiversity of the existing plant species in a fine-grained scenario. Robust deep learning architectures have been used to improve the classification performance in such a fine-grained pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c3ae1e29407ccf41e24c85bc05b4a5c8
https://doi.org/10.1016/j.neucom.2021.10.015
https://doi.org/10.1016/j.neucom.2021.10.015
This paper presents a deep learning approach for image retrieval and pattern spotting in digital collections of historical documents. First, a region proposal algorithm detects object candidates in the document page images. Next, deep learning models
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3b979167f322834a32b11bd41b6ef23a
http://arxiv.org/abs/2208.02397
http://arxiv.org/abs/2208.02397
Publikováno v:
Information Sciences. 526:20-38
In this paper, we present an incremental variant of the Twin Support Vector Machine (TWSVM) called Fuzzy Bounded Twin Support Vector Machine (FBTWSVM) to deal with large datasets and to learn from data streams. We combine the TWSVM with a fuzzy membe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a36c9a9f00c1803ab2815ec27a700bd8
https://doi.org/10.1016/j.ins.2020.03.038
https://doi.org/10.1016/j.ins.2020.03.038
Publikováno v:
IEEE Transactions on Information Forensics and Security. 15:2147-2159
Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the safety of mac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc7bc409a8da7dda02808563f85dec5d
https://doi.org/10.1109/tifs.2019.2956591
https://doi.org/10.1109/tifs.2019.2956591
Publikováno v:
Signal, Image and Video Processing. 13:975-983
This paper presents the main aspects of the design of an image acquisition and processing approach that can be inserted into thermoelectric metal pipe systems and travel inside the pipes to capture images from the inner surface of such pipes for furt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85331dd1dd7af3cce8be2cbd789bb42c
https://doi.org/10.1007/s11760-019-01435-2
https://doi.org/10.1007/s11760-019-01435-2
This paper proposes a new defense approach for counteracting state-of-the-art white and black-box adversarial attack algorithms. Our approach fits into the implicit reactive defense algorithm category since it does not directly manipulate the potenti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0c0cf6f3c350a0c9582ac18fb7f7d342
http://arxiv.org/abs/2103.14717
http://arxiv.org/abs/2103.14717
Publikováno v:
ICASSP
In this paper we propose a novel defense approach against end-to-end adversarial attacks developed to fool advanced speech-to-text systems such as DeepSpeech and Lingvo. Unlike conventional defense approaches, the proposed approach does not directly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e2baed1fe37b5cfac741f56ee4d3e28
http://arxiv.org/abs/2010.11352
http://arxiv.org/abs/2010.11352
Autor:
Sajjad Abdoli, Alessandro L. Koerich, Mohammad Esmailpour, Karl Michel Koerich, Alceu S. Britto
Publikováno v:
IJCNN
This paper shows the susceptibility of spectrogram-based audio classifiers to adversarial attacks and the transferability of such attacks to audio waveforms. Some commonly used adversarial attacks to images have been applied to Mel-frequency and shor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::529caf97da4684cfb26b0e044a028de0
https://doi.org/10.1109/ijcnn48605.2020.9207309
https://doi.org/10.1109/ijcnn48605.2020.9207309
Autor:
Alessandro L. Koerich, Alceu S. Britto, Luiz S. Oliveira, Steve Tsham Mpinda Ataky, Jonathan de Matos
Publikováno v:
IJCNN
Data imbalance is a major problem that affects several machine learning (ML) algorithms. Such a problem is troublesome because most of the ML algorithms attempt to optimize a loss function that does not take into account the data imbalance. According
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::314c5569740b9ef0703c5d12cfa4f1b9
https://doi.org/10.1109/ijcnn48605.2020.9206855
https://doi.org/10.1109/ijcnn48605.2020.9206855