Zobrazeno 1 - 10
of 191
pro vyhledávání: '"Li, Jiangyun"'
Autor:
Shen, Haoran, Zhang, Yifu, Wang, Wenxuan, Chen, Chen, Liu, Jing, Song, Shanshan, Li, Jiangyun
Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for me
Externí odkaz:
http://arxiv.org/abs/2310.18656
Autor:
Wang, Wenxuan, Liu, Jing, He, Xingjian, Zhang, Yisi, Chen, Chen, Shen, Jiachen, Zhang, Yan, Li, Jiangyun
Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and text, most
Externí odkaz:
http://arxiv.org/abs/2305.11481
Autor:
Shen, Jiachen, Wang, Wenxuan, Chen, Chen, Jiao, Jianbo, Liu, Jing, Zhang, Yan, Song, Shanshan, Li, Jiangyun
The "pre-training then fine-tuning (FT)" paradigm is widely adopted to boost the model performance of deep learning-based methods for medical volumetric segmentation. However, conventional full FT incurs high computational and memory costs. Thus, it
Externí odkaz:
http://arxiv.org/abs/2304.10880
Autor:
Wang, Wenxuan, Wang, Jing, Chen, Chen, Jiao, Jianbo, Sun, Lichao, Cai, Yuanxiu, Song, Shanshan, Li, Jiangyun
The research community has witnessed the powerful potential of self-supervised Masked Image Modeling (MIM), which enables the models capable of learning visual representation from unlabeled data.In this paper, to incorporate both the crucial global s
Externí odkaz:
http://arxiv.org/abs/2304.10864
Autor:
Zhang, Bo1 (AUTHOR) zb_ccric@163.com, Li, Jiangyun2,3 (AUTHOR) leejy@ustb.edu.cn, Tang, Haicheng2,3 (AUTHOR) m202210556@xs.ustb.edu.cn, Liu, Xi2,3 (AUTHOR)
Publikováno v:
Sensors (14248220). Sep2024, Vol. 24 Issue 17, p5580. 14p.
There is a key problem in the medical visual question answering task that how to effectively realize the feature fusion of language and medical images with limited datasets. In order to better utilize multi-scale information of medical images, previo
Externí odkaz:
http://arxiv.org/abs/2211.05991
The contextual information is critical for various computer vision tasks, previous works commonly design plug-and-play modules and structural losses to effectively extract and aggregate the global context. These methods utilize fine-label to optimize
Externí odkaz:
http://arxiv.org/abs/2207.01417
For 3D medical image (e.g. CT and MRI) segmentation, the difficulty of segmenting each slice in a clinical case varies greatly. Previous research on volumetric medical image segmentation in a slice-by-slice manner conventionally use the identical 2D
Externí odkaz:
http://arxiv.org/abs/2206.06575
The encoder-decoder architecture is widely used as a lightweight semantic segmentation network. However, it struggles with a limited performance compared to a well-designed Dilated-FCN model for two major problems. First, commonly used upsampling met
Externí odkaz:
http://arxiv.org/abs/2204.04363
Objective: Magnetic resonance imaging (MRI) has been widely used for the analysis and diagnosis of brain diseases. Accurate and automatic brain tumor segmentation is of paramount importance for radiation treatment. However, low tissue contrast in tum
Externí odkaz:
http://arxiv.org/abs/2203.15383