Zobrazeno 1 - 10
of 143
pro vyhledávání: '"He, Shuo"'
Multimodal contrastive learning methods (e.g., CLIP) have shown impressive zero-shot classification performance due to their strong ability to joint representation learning for visual and textual modalities. However, recent research revealed that mul
Externí odkaz:
http://arxiv.org/abs/2405.15269
Partial-label learning (PLL) relies on a key assumption that the true label of each training example must be in the candidate label set. This restrictive assumption may be violated in complex real-world scenarios, and thus the true label of some coll
Externí odkaz:
http://arxiv.org/abs/2307.00553
In contrast to the standard learning paradigm where all classes can be observed in training data, learning with augmented classes (LAC) tackles the problem where augmented classes unobserved in the training data may emerge in the test phase. Previous
Externí odkaz:
http://arxiv.org/abs/2306.06894
Autor:
Liang, Yan, He, Shuo, Liu, Qing, Liu, Tao, Tan, Yiyi, Peng, Tianyuan, Huang, Conggai, Lu, Xiaomei, Zheng, Shutao
Publikováno v:
In BBA - Molecular Cell Research October 2024 1871(7)
Autor:
Gu, Junchi, Wei, Guangtao, He, Yuliang, Zhang, Yi, Xiong, Deyuan, Zhang, Linye, Zhou, Yanling, He, Shuo
Publikováno v:
In Journal of Water Process Engineering December 2024 68
Autor:
Liang, Yan, He, Shuo, Tan, Yiyi, Liu, Qing, Zhao, Feng, Liu, Tao, Huang, Conggai, Lu, Xiaomei, Zheng, Shutao
Publikováno v:
In Heliyon 15 January 2024 10(1)
Multi-label learning deals with the problem that each instance is associated with multiple labels simultaneously. Most of the existing approaches aim to improve the performance of multi-label learning by exploiting label correlations. Although the da
Externí odkaz:
http://arxiv.org/abs/2004.08113
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
It is well-known that exploiting label correlations is crucially important to multi-label learning. Most of the existing approaches take label correlations as prior knowledge, which may not correctly characterize the real relationships among labels.
Externí odkaz:
http://arxiv.org/abs/1902.03047
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.