Zobrazeno 1 - 10
of 170
pro vyhledávání: '"Huang, Sheng Jun"'
Due to the lack of extensive precisely-annotated multi-label data in real word, semi-supervised multi-label learning (SSMLL) has gradually gained attention. Abundant knowledge embedded in vision-language models (VLMs) pre-trained on large-scale image
Externí odkaz:
http://arxiv.org/abs/2412.18842
Offline-to-online (O2O) reinforcement learning (RL) provides an effective means of leveraging an offline pre-trained policy as initialization to improve performance rapidly with limited online interactions. Recent studies often design fine-tuning str
Externí odkaz:
http://arxiv.org/abs/2412.18855
Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the transition to predicted probabilities from logits would obscure certain
Externí odkaz:
http://arxiv.org/abs/2411.08937
Active learning (AL) has achieved great success by selecting the most valuable examples from unlabeled data. However, they usually deteriorate in real scenarios where open-set noise gets involved, which is studied as open-set annotation (OSA). In thi
Externí odkaz:
http://arxiv.org/abs/2409.17607
Large language models (LLMs) have shown great potential in code-related tasks, yet open-source models lag behind their closed-source counterparts. To bridge this performance gap, existing methods generate vast amounts of synthetic data for fine-tunin
Externí odkaz:
http://arxiv.org/abs/2408.02193
Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations. Unlike semi-supervised learning, one cannot select the most probable label
Externí odkaz:
http://arxiv.org/abs/2407.18624
Current knowledge distillation (KD) methods primarily focus on transferring various structured knowledge and designing corresponding optimization goals to encourage the student network to imitate the output of the teacher network. However, introducin
Externí odkaz:
http://arxiv.org/abs/2407.03719
Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently. Existing AL algorithms often rely on iterative model training, which can be computationally expensive, parti
Externí odkaz:
http://arxiv.org/abs/2405.14121
Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method called \emph
Externí odkaz:
http://arxiv.org/abs/2405.14111
Autor:
Hemati, Hamed, Pellegrini, Lorenzo, Duan, Xiaotian, Zhao, Zixuan, Xia, Fangfang, Masana, Marc, Tscheschner, Benedikt, Veas, Eduardo, Zheng, Yuxiang, Zhao, Shiji, Li, Shao-Yuan, Huang, Sheng-Jun, Lomonaco, Vincenzo, van de Ven, Gido M.
Publikováno v:
Neural Networks, March 2025: Vol 183, 106920
Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not often con
Externí odkaz:
http://arxiv.org/abs/2405.04101