Výsledky vyhledávání

Report

AxWin Transformer: A Context-Aware Vision Transformer Backbone with Axial Windows

Autor: Lin, Fangjian, Ma, Yizhe, Wu, Sitong, Yu, Long, Tian, Shengwei

Recently Transformer has shown good performance in several vision tasks due to its powerful modeling capabilities. To reduce the quadratic complexity caused by the attention, some outstanding work restricts attention to local regions or extends axial

Externí odkaz: http://arxiv.org/abs/2305.01280

Zobrazit plný text záznamu

Report

Exploring vision transformer layer choosing for semantic segmentation

Autor: Lin, Fangjian, Ma, Yizhe, Tian, Shengwei

Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last layer of features aiming to achieve higher performance in dense predict

Externí odkaz: http://arxiv.org/abs/2305.01279

Zobrazit plný text záznamu

Report

PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation

Autor: Ma, Yizhe, Lin, Fangjian, Wu, Sitong, Tian, Shengwei, Yu, Long

The lightweight MLP-based decoder has become increasingly promising for semantic segmentation. However, the channel-wise MLP cannot expand the receptive fields, lacking the context modeling capacity, which is critical to semantic segmentation. In thi

Externí odkaz: http://arxiv.org/abs/2305.00671

Zobrazit plný text záznamu

Akademický článek

Activation of LXR signaling ameliorates apoptosis of alveolar epithelial cells in Bronchopulmonary dysplasia.

Autor: Ma, Yizhe^1,2 (AUTHOR), Wang, Yameng² (AUTHOR), Xie, Anni¹ (AUTHOR), Wang, Luchun² (AUTHOR), Zhang, Yuqiong² (AUTHOR), Tao, Mingyan² (AUTHOR), Deng, Xianhui^1,2 (AUTHOR), Bao, Zhidan² (AUTHOR) baodandancandy@126.com, Yu, Renqiang¹ (AUTHOR) yurenqiang553@163.com

Publikováno v: Respiratory Research. 11/7/2024, Vol. 25 Issue 1, p1-13. 13p.