Zobrazeno 1 - 10
of 223
pro vyhledávání: '"Daniel S. Yeung"'
Autor:
Patrick P. K. Chan, Qiuxia Li, Yinfeng Fang, Linyi Xu, Kairu Li, Honghai Liu, Daniel S. Yeung
Publikováno v:
IEEE Transactions on Human-Machine Systems. 52:1271-1280
Publikováno v:
Information Sciences. 643:119120
Publikováno v:
Information Sciences. 548:450-460
Recent studies indicate that a classifier is vulnerable in an adversarial environment. The label flipping attack aims to mislead the training process. Some countermeasures have been proposed, but are usually designed for a particular classifier only,
Publikováno v:
International Journal of Machine Learning and Cybernetics. 12:103-116
A causative attack which manipulates training samples to mislead learning is a common attack scenario. Current countermeasures reduce the influence of the attack to a classifier with the loss of generalization ability. Therefore, the collected sample
Publikováno v:
IEEE Transactions on Cybernetics. 49:3844-3858
Images are uploaded to the Internet over time which makes concept drifting and distribution change in semantic classes unavoidable. Current hashing methods being trained using a given static database may not be suitable for nonstationary semantic ima
Publikováno v:
IJCNN
Feature selection plays an important role in machine learning in order to reduce model complexity and extract more meaningful information. The recent studies indicate that not only the generalization ability but also the security should be considered
Publikováno v:
IJCNN
Image-level weakly supervised semantic segmentation (WSSS) reduces the cost of semantic segmentation significantly as only category labels are required. In the WSSS pipeline, the initially obtained seed areas are imprecise and should be refined. Affi
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030863616
ICANN (1)
ICANN (1)
Deep Reinforcement Learning models inherit not only generalization abilities but also vulnerabilities under adversarial attacks from Deep Neural Networks. The recent external model based defense method for Reinforcement Learning (RL) detects and corr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::461e3df7332d8076f4e3c450fe699d30
https://doi.org/10.1007/978-3-030-86362-3_4
https://doi.org/10.1007/978-3-030-86362-3_4
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030863647
ICANN (3)
ICANN (3)
Weakly supervised semantic segmentation (WSSS) methods are more flexible and less costly than supervised ones since no pixel-level annotation is required. Class activation maps (CAMs) are commonly used in existing WSSS methods with image-level annota
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d81ac0dd82baba0621883b5c4e3a327c
https://doi.org/10.1007/978-3-030-86365-4_38
https://doi.org/10.1007/978-3-030-86365-4_38
Publikováno v:
Computer Vision and Image Understanding. 217:103347