Zobrazeno 1 - 10
of 104
pro vyhledávání: '"Yin, Wenzhe"'
Domain adaptation aims to use training data from one or multiple source domains to learn a hypothesis that can be generalized to a different, but related, target domain. As such, having a reliable measure for evaluating the discrepancy of both margin
Externí odkaz:
http://arxiv.org/abs/2405.19978
Few-shot point cloud segmentation seeks to generate per-point masks for previously unseen categories, using only a minimal set of annotated point clouds as reference. Existing prototype-based methods rely on support prototypes to guide the segmentati
Externí odkaz:
http://arxiv.org/abs/2401.16051
Autor:
Hu, Vincent Tao, Yin, Wenzhe, Ma, Pingchuan, Chen, Yunlu, Fernando, Basura, Asano, Yuki M, Gavves, Efstratios, Mettes, Pascal, Ommer, Bjorn, Snoek, Cees G. M.
Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation. In this p
Externí odkaz:
http://arxiv.org/abs/2312.08895
Autor:
Liu, Jie, Bao, Yanqi, Yin, Wenzhe, Wang, Haochen, Gao, Yang, Sonke, Jan-Jakob, Gavves, Efstratios
Few-shot semantic segmentation (FSS) aims to achieve novel objects segmentation with only a few annotated samples and has made great progress recently. Most of the existing FSS models focus on the feature matching between support and query to tackle
Externí odkaz:
http://arxiv.org/abs/2301.03194
Graph sparsification aims to reduce the number of edges of a graph while maintaining its structural properties. In this paper, we propose the first general and effective information-theoretic formulation of graph sparsification, by taking inspiration
Externí odkaz:
http://arxiv.org/abs/2206.00118
Publikováno v:
In Progress in Nuclear Energy November 2024 176
Publikováno v:
In Annals of Nuclear Energy February 2025 211
Autor:
Jiang, Yingying, Xia, Hong, Zhou, Zhuoran, Yin, Wenzhe, Jia, Zhujun, Huang, Xueying, Zhang, Jiyu, Zhu, Yihu
Publikováno v:
In Annals of Nuclear Energy February 2025 211
Publikováno v:
In Annals of Nuclear Energy May 2024 199
Continual learning (CL) studies the problem of learning a sequence of tasks, one at a time, such that the learning of each new task does not lead to the deterioration in performance on the previously seen ones while exploiting previously learned feat
Externí odkaz:
http://arxiv.org/abs/2011.01168