Zobrazeno 1 - 10
of 1 853
pro vyhledávání: '"Wang, Liyuan"'
The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting. To sustain these advantages for sequentially arriving tasks, a prom
Externí odkaz:
http://arxiv.org/abs/2407.05229
Autor:
Zhang, Hao, Jiang, Longxiang, Chu, Xinkun, Wen, Yong, Li, Luxiong, Xiao, Yonghao, Wang, Liyuan
The great success of Physics-Informed Neural Networks (PINN) in solving partial differential equations (PDEs) has significantly advanced our simulation and understanding of complex physical systems in science and engineering. However, many PINN-like
Externí odkaz:
http://arxiv.org/abs/2405.20000
Autor:
Chen, Jiachen, Huang, Danyang, Wang, Liyuan, Lunetta, Kathryn L., Mukherjee, Debarghya, Cheng, Huimin
Node classification is a fundamental task, but obtaining node classification labels can be challenging and expensive in many real-world scenarios. Transfer learning has emerged as a promising solution to address this challenge by leveraging knowledge
Externí odkaz:
http://arxiv.org/abs/2405.16672
The vision-language pre-training has enabled deep models to make a huge step forward in generalizing across unseen domains. The recent learning method based on the vision-language pre-training model is a great tool for domain generalization and can s
Externí odkaz:
http://arxiv.org/abs/2404.18758
Action Quality Assessment (AQA) is pivotal for quantifying actions across domains like sports and medical care. Existing methods often rely on pre-trained backbones from large-scale action recognition datasets to boost performance on smaller AQA data
Externí odkaz:
http://arxiv.org/abs/2404.13999
To accommodate real-world dynamics, artificial intelligence systems need to cope with sequentially arriving content in an online manner. Beyond regular Continual Learning (CL) attempting to address catastrophic forgetting with offline training of eac
Externí odkaz:
http://arxiv.org/abs/2404.00417
Autor:
Zhou, Kanglei, Wang, Liyuan, Zhang, Xingxing, Shum, Hubert P. H., Li, Frederick W. B., Li, Jianguo, Liang, Xiaohui
Action Quality Assessment (AQA) evaluates diverse skills but models struggle with non-stationary data. We propose Continual AQA (CAQA) to refine models using sparse new data. Feature replay preserves memory without storing raw inputs. However, the mi
Externí odkaz:
http://arxiv.org/abs/2403.04398
Autor:
Yuan, Ziqi, Wang, Liyuan, Ding, Wenbo, Zhang, Xingxing, Zhong, Jiachen, Ai, Jianyong, Li, Jianmin, Zhu, Jun
In real-world applications, an object detector often encounters object instances from new classes and needs to accommodate them effectively. Previous work formulated this critical problem as incremental object detection (IOD), which assumes the objec
Externí odkaz:
http://arxiv.org/abs/2401.05362
Autor:
Zhu, Zheqing, Braz, Rodrigo de Salvo, Bhandari, Jalaj, Jiang, Daniel, Wan, Yi, Efroni, Yonathan, Wang, Liyuan, Xu, Ruiyang, Guo, Hongbo, Nikulkov, Alex, Korenkevych, Dmytro, Dogan, Urun, Cheng, Frank, Wu, Zheng, Xu, Wanqiao
Reinforcement Learning (RL) offers a versatile framework for achieving long-term goals. Its generality allows us to formalize a wide range of problems that real-world intelligent systems encounter, such as dealing with delayed rewards, handling parti
Externí odkaz:
http://arxiv.org/abs/2312.03814
In this work, we present a general framework for continual learning of sequentially arrived tasks with the use of pre-training, which has emerged as a promising direction for artificial intelligence systems to accommodate real-world dynamics. From a
Externí odkaz:
http://arxiv.org/abs/2310.13888