Zobrazeno 1 - 10
of 514
pro vyhledávání: '"LI Zhuowei"'
Autor:
Li, Zhuowei, Xu, Zihao, Han, Ligong, Gao, Yunhe, Wen, Song, Liu, Di, Wang, Hao, Metaxas, Dimitris N.
In-context Learning (ICL) empowers large language models (LLMs) to adapt to unseen tasks during inference by prefixing a few demonstration examples prior to test queries. Despite its versatility, ICL incurs substantial computational and memory overhe
Externí odkaz:
http://arxiv.org/abs/2405.14660
This paper introduces GAgent: an Gripping Agent designed for open-world environments that provides advanced cognitive abilities via VLM agents and flexible grasping abilities with variable stiffness soft grippers. GAgent comprises three primary compo
Externí odkaz:
http://arxiv.org/abs/2403.10850
Autor:
Liu, Di, Yu, Xiang, Ye, Meng, Zhangli, Qilong, Li, Zhuowei, Zhang, Zhixing, Metaxas, Dimitris N.
Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics. By leveraging a set of primitives to represent the target shape, recent methods have achieved promising results. However, these methods e
Externí odkaz:
http://arxiv.org/abs/2309.12594
Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation
A major focus of clinical imaging workflow is disease diagnosis and management, leading to medical imaging datasets strongly tied to specific clinical objectives. This scenario has led to the prevailing practice of developing task-specific segmentati
Externí odkaz:
http://arxiv.org/abs/2306.02416
In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting. However, challenges related to semantic drift and prototype interference persis
Externí odkaz:
http://arxiv.org/abs/2303.09447
Autor:
Li, Zhuowei, Gao, Yibo, Zha, Zhenzhou, HU, Zhiqiang, Xia, Qing, Zhang, Shaoting, Metaxas, Dimitris N.
Neural architecture search (NAS) algorithms save tremendous labor from human experts. Recent advancements further reduce the computational overhead to an affordable level. However, it is still cumbersome to deploy the NAS techniques in real-world app
Externí odkaz:
http://arxiv.org/abs/2206.04125
Autor:
Li, Zhuowei, Wang, Junlin, Lu, Siye, Liu, Jia, Zeng, Jiangjie, Gao, Hanxiao, Liu, Chunyu, Guo, Wenbin
Publikováno v:
In Chemical Engineering Journal 1 November 2024 499
Publikováno v:
In Journal of Colloid And Interface Science 15 January 2025 678 Part A:209-217
Autor:
Li, Zhuowei, Liu, Zihao, Hu, Zhiqiang, Xia, Qing, Xiong, Ruiqin, Zhang, Shaoting, Metaxas, Dimitris, Jiang, Tingting
Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning. However, the laborious and expensive annotation process lags down the speed of further advances. Contrastive learning
Externí odkaz:
http://arxiv.org/abs/2201.08779
Deep learning has demonstrated significant improvements in medical image segmentation using a sufficiently large amount of training data with manual labels. Acquiring well-representative labels requires expert knowledge and exhaustive labors. In this
Externí odkaz:
http://arxiv.org/abs/2105.12924