LSKSANet: A Novel Architecture for Remote Sensing Image Semantic Segmentation Leveraging Large Selective Kernel and Sparse Attention Mechanism
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911900586999808 |
|---|---|
| author | Fu, Miao Gao, Feng Hua, Ruzhuang Gan, Yanhai Zhou, Xiaowei Zhou, Yang |
| author_facet | Fu, Miao Gao, Feng Hua, Ruzhuang Gan, Yanhai Zhou, Xiaowei Zhou, Yang |
| contents | In this paper, we proposed large selective kernel and sparse attention network (LSKSANet) for remote sensing image semantic segmentation. The LSKSANet is a lightweight network that effectively combines convolution with sparse attention mechanisms. Specifically, we design large selective kernel module to decomposing the large kernel into a series of depth-wise convolutions with progressively increasing dilation rates, thereby expanding the receptive field without significantly increasing the computational burden. In addition, we introduce the sparse attention to keep the most useful self-attention values for better feature aggregation. Experimental results on the Vaihingen and Postdam datasets demonstrate the superior performance of the proposed LSKSANet over state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01228 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LSKSANet: A Novel Architecture for Remote Sensing Image Semantic Segmentation Leveraging Large Selective Kernel and Sparse Attention Mechanism Fu, Miao Gao, Feng Hua, Ruzhuang Gan, Yanhai Zhou, Xiaowei Zhou, Yang Image and Video Processing In this paper, we proposed large selective kernel and sparse attention network (LSKSANet) for remote sensing image semantic segmentation. The LSKSANet is a lightweight network that effectively combines convolution with sparse attention mechanisms. Specifically, we design large selective kernel module to decomposing the large kernel into a series of depth-wise convolutions with progressively increasing dilation rates, thereby expanding the receptive field without significantly increasing the computational burden. In addition, we introduce the sparse attention to keep the most useful self-attention values for better feature aggregation. Experimental results on the Vaihingen and Postdam datasets demonstrate the superior performance of the proposed LSKSANet over state-of-the-art methods. |
| title | LSKSANet: A Novel Architecture for Remote Sensing Image Semantic Segmentation Leveraging Large Selective Kernel and Sparse Attention Mechanism |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2406.01228 |