Zobrazeno 1 - 10
of 687
pro vyhledávání: '"Yin, Yilong"'
Few-Shot Learning (FSL) aims to recognize new classes with limited labeled data. Recent studies have attempted to address the challenge of rare samples with textual prompts to modulate visual features. However, they usually struggle to capture comple
Externí odkaz:
http://arxiv.org/abs/2410.10227
Autor:
Wang, Qikai, He, Rundong, Gong, Yongshun, Ren, Chunxiao, Sun, Haoliang, Huang, Xiaoshui, Yin, Yilong
Semi-supervised learning can significantly boost model performance by leveraging unlabeled data, particularly when labeled data is scarce. However, real-world unlabeled data often contain unseen-class samples, which can hinder the classification of s
Externí odkaz:
http://arxiv.org/abs/2405.16093
Noisy labels significantly hinder the accuracy and generalization of machine learning models, particularly due to ambiguous instance features. Traditional techniques that attempt to correct noisy labels directly, such as those using transition matric
Externí odkaz:
http://arxiv.org/abs/2405.12969
Policy-based methods have achieved remarkable success in solving challenging reinforcement learning problems. Among these methods, off-policy policy gradient methods are particularly important due to that they can benefit from off-policy data. Howeve
Externí odkaz:
http://arxiv.org/abs/2405.02572
Autor:
Yu, Jun, Dai, Yutong, Liu, Xiaokang, Huang, Jin, Shen, Yishan, Zhang, Ke, Zhou, Rong, Adhikarla, Eashan, Ye, Wenxuan, Liu, Yixin, Kong, Zhaoming, Zhang, Kai, Yin, Yilong, Namboodiri, Vinod, Davison, Brian D., Moore, Jason H., Chen, Yong
MTL is a learning paradigm that effectively leverages both task-specific and shared information to address multiple related tasks simultaneously. In contrast to STL, MTL offers a suite of benefits that enhance both the training process and the infere
Externí odkaz:
http://arxiv.org/abs/2404.18961
Few-shot OOD detection focuses on recognizing out-of-distribution (OOD) images that belong to classes unseen during training, with the use of only a small number of labeled in-distribution (ID) images. Up to now, a mainstream strategy is based on lar
Externí odkaz:
http://arxiv.org/abs/2404.00323
Autor:
Han, Zhongyi, Zhou, Guanglin, He, Rundong, Wang, Jindong, Wu, Tailin, Yin, Yilong, Khan, Salman, Yao, Lina, Liu, Tongliang, Zhang, Kun
In machine learning, generalization against distribution shifts -- where deployment conditions diverge from the training scenarios -- is crucial, particularly in fields like climate modeling, biomedicine, and autonomous driving. The emergence of foun
Externí odkaz:
http://arxiv.org/abs/2312.07424
Imitation learning aims to solve the problem of defining reward functions in real-world decision-making tasks. The current popular approach is the Adversarial Imitation Learning (AIL) framework, which matches expert state-action occupancy measures to
Externí odkaz:
http://arxiv.org/abs/2312.06348
Autor:
Zan, Daoguang, Chen, Bei, Gong, Yongshun, Cao, Junzhi, Zhang, Fengji, Wu, Bingchao, Guan, Bei, Yin, Yilong, Wang, Yongji
Large language models (LLMs), such as Codex and GPT-4, have recently showcased their remarkable code generation abilities, facilitating a significant boost in coding efficiency. This paper will delve into utilizing LLMs for code generation in private
Externí odkaz:
http://arxiv.org/abs/2307.15370
Meta-learning methods typically follow a two-loop framework, where each loop potentially suffers from notorious overfitting, hindering rapid adaptation and generalization to new tasks. Existing schemes solve it by enhancing the mutual-exclusivity or
Externí odkaz:
http://arxiv.org/abs/2306.08460