تقرير
Realtime Global Attention Network for Semantic Segmentation
| العنوان: | Realtime Global Attention Network for Semantic Segmentation |
|---|---|
| المؤلفون: | Mo, Xi, Chen, Xiangyu |
| المصدر: | IEEE Robotics and Automation Letters 7(2022).1574-1580 |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | In this paper, we proposed an end-to-end realtime global attention neural network (RGANet) for the challenging task of semantic segmentation. Different from the encoding strategy deployed by self-attention paradigms, the proposed global attention module encodes global attention via depth-wise convolution and affine transformations. The integration of these global attention modules into a hierarchy architecture maintains high inferential performance. In addition, an improved evaluation metric, namely MGRID, is proposed to alleviate the negative effect of non-convex, widely scattered ground-truth areas. Results from extensive experiments on state-of-the-art architectures for semantic segmentation manifest the leading performance of proposed approaches for robotic monocular visual perception. Comment: Ver1.0 for RA-L with ICRA presentation |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1109/LRA.2022.3140443 |
| URL الوصول: | http://arxiv.org/abs/2112.12939 |
| رقم الأكسشن: | edsarx.2112.12939 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1109/LRA.2022.3140443 |
|---|