Zobrazeno 1 - 10
of 1 629
pro vyhledávání: '"Wu, Yicheng"'
Autor:
Wu, Yicheng, Luo, Xiangde, Xu, Zhe, Guo, Xiaoqing, Ju, Lie, Ge, Zongyuan, Liao, Wenjun, Cai, Jianfei
Annotation ambiguity due to inherent data uncertainties such as blurred boundaries in medical scans and different observer expertise and preferences has become a major obstacle for training deep-learning based medical image segmentation models. To ad
Externí odkaz:
http://arxiv.org/abs/2403.13417
Annotation scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation, restricting their deployment in clinical scenarios. To address it, semi-supervised learning by exploiting abundant unlabeled da
Externí odkaz:
http://arxiv.org/abs/2311.11686
New lesion segmentation is essential to estimate the disease progression and therapeutic effects during multiple sclerosis (MS) clinical treatments. However, the expensive data acquisition and expert annotation restrict the feasibility of applying la
Externí odkaz:
http://arxiv.org/abs/2307.04513
Semi-supervised learning (SSL) has attracted much attention since it reduces the expensive costs of collecting adequate well-labeled training data, especially for deep learning methods. However, traditional SSL is built upon an assumption that labele
Externí odkaz:
http://arxiv.org/abs/2304.04059
Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used
Externí odkaz:
http://arxiv.org/abs/2303.05164
Autor:
Kim, Junho, Kim, Young Min, Wu, Yicheng, Zahreddine, Ramzi, Welge, Weston A., Krishnan, Gurunandan, Ma, Sizhuo, Wang, Jian
We present a robust, privacy-preserving visual localization algorithm using event cameras. While event cameras can potentially make robust localization due to high dynamic range and small motion blur, the sensors exhibit large domain gaps making it d
Externí odkaz:
http://arxiv.org/abs/2212.03177
Flash illumination is widely used in imaging under low-light environments. However, illumination intensity falls off with propagation distance quadratically, which poses significant challenges for flash imaging at a long distance. We propose a new fl
Externí odkaz:
http://arxiv.org/abs/2207.12570
Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training.
Externí odkaz:
http://arxiv.org/abs/2207.09084
Structured light (SL) systems acquire high-fidelity 3D geometry with active illumination projection. Conventional systems exhibit challenges when working in environments with strong ambient illumination, global illumination and cross-device interfere
Externí odkaz:
http://arxiv.org/abs/2206.09243