Zobrazeno 1 - 10
of 120
pro vyhledávání: '"Li Zhongnian"'
Learning from Multi-Positive and Unlabeled (MPU) data has gradually attracted significant attention from practical applications. Unfortunately, the risk of MPU also suffer from the shift of minimum risk, particularly when the models are very flexible
Externí odkaz:
http://arxiv.org/abs/2412.02240
Annotating data for sensitive labels (e.g., disease, smoking) poses a potential threats to individual privacy in many real-world scenarios. To cope with this problem, we propose a novel setting to protect privacy of each instance, namely learning fro
Externí odkaz:
http://arxiv.org/abs/2412.02230
Recent advances in vision-language models (VLM) have demonstrated remarkable capability in image classification. These VLMs leverage a predefined set of categories to construct text prompts for zero-shot reasoning. However, in more open-ended domains
Externí odkaz:
http://arxiv.org/abs/2411.17406
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
In multi-label classification, each training instance is associated with multiple class labels simultaneously. Unfortunately, collecting the fully precise class labels for each training instance is time- and labor-consuming for real-world application
Externí odkaz:
http://arxiv.org/abs/2403.16482
Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite being a common approach to miti
Externí odkaz:
http://arxiv.org/abs/2403.16469
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
Annotating multi-class instances is a crucial task in the field of machine learning. Unfortunately, identifying the correct class label from a long sequence of candidate labels is time-consuming and laborious. To alleviate this problem, we design a n
Externí odkaz:
http://arxiv.org/abs/2302.00299
Publikováno v:
Electronic Research Archive. 2024, Vol. 32 Issue 10, p1-15. 15p.
Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compared with standard supervised learning. Unfortunately, most previous CLL
Externí odkaz:
http://arxiv.org/abs/2211.10701