Zobrazeno 1 - 10
of 87
pro vyhledávání: '"Sun, Tongfeng"'
Weakly supervised learning has recently achieved considerable success in reducing annotation costs and label noise. Unfortunately, existing weakly supervised learning methods are short of ability in generating reliable labels via pre-trained vision-l
Externí odkaz:
http://arxiv.org/abs/2405.15228
Multi-abel Learning (MLL) often involves the assignment of multiple relevant labels to each instance, which can lead to the leakage of sensitive information (such as smoking, diseases, etc.) about the instances. However, existing MLL suffer from fail
Externí odkaz:
http://arxiv.org/abs/2312.13312
Positive Unlabeled (PU) learning aims to learn a binary classifier from only positive and unlabeled data, which is utilized in many real-world scenarios. However, existing PU learning algorithms cannot deal with the real-world challenge in an open an
Externí odkaz:
http://arxiv.org/abs/2207.13274
Publikováno v:
In Neural Networks February 2024 170:453-467
Publikováno v:
In Neural Networks April 2022 148:155-165
Publikováno v:
In Signal Processing: Image Communication November 2021 99
Publikováno v:
In Information Sciences April 2020 516:142-157
Publikováno v:
In Neurocomputing 15 February 2020 377:95-102
Autor:
Zhang, Bobin, Shao, Xiuyan, Chen, Wei, Bi, Fangming, Fang, Weidong, Sun, Tongfeng, Tang, Chaogang
Publikováno v:
In Image and Vision Computing September 2019 89:211-221
Publikováno v:
In Information Sciences November 2017 415-416:233-246