Segregation and Context Aggregation Network for Real-time Cloud Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908328171405312 |
|---|---|
| author | Li, Yijie Wang, Hewei Zhang, Jiayi You, Jinjiang Xu, Jinfeng Wu, Puzhen Xiao, Yunzhong Dev, Soumyabrata |
| author_facet | Li, Yijie Wang, Hewei Zhang, Jiayi You, Jinjiang Xu, Jinfeng Wu, Puzhen Xiao, Yunzhong Dev, Soumyabrata |
| contents | Cloud segmentation from intensity images is a pivotal task in atmospheric science and computer vision, aiding weather forecasting and climate analysis. Ground-based sky/cloud segmentation extracts clouds from images for further feature analysis. Existing methods struggle to balance segmentation accuracy and computational efficiency, limiting real-world deployment on edge devices, so we introduce SCANet, a novel lightweight cloud segmentation model featuring Segregation and Context Aggregation Module (SCAM), which refines rough segmentation maps into weighted sky and cloud features processed separately. SCANet achieves state-of-the-art performance while drastically reducing computational complexity. SCANet-large (4.29M) achieves comparable accuracy to state-of-the-art methods with 70.9% fewer parameters. Meanwhile, SCANet-lite (90K) delivers 1390 fps in FP16, surpassing real-time standards. Additionally, we propose an efficient pre-training strategy that enhances performance even without ImageNet pre-training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14178 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Segregation and Context Aggregation Network for Real-time Cloud Segmentation Li, Yijie Wang, Hewei Zhang, Jiayi You, Jinjiang Xu, Jinfeng Wu, Puzhen Xiao, Yunzhong Dev, Soumyabrata Computer Vision and Pattern Recognition Cloud segmentation from intensity images is a pivotal task in atmospheric science and computer vision, aiding weather forecasting and climate analysis. Ground-based sky/cloud segmentation extracts clouds from images for further feature analysis. Existing methods struggle to balance segmentation accuracy and computational efficiency, limiting real-world deployment on edge devices, so we introduce SCANet, a novel lightweight cloud segmentation model featuring Segregation and Context Aggregation Module (SCAM), which refines rough segmentation maps into weighted sky and cloud features processed separately. SCANet achieves state-of-the-art performance while drastically reducing computational complexity. SCANet-large (4.29M) achieves comparable accuracy to state-of-the-art methods with 70.9% fewer parameters. Meanwhile, SCANet-lite (90K) delivers 1390 fps in FP16, surpassing real-time standards. Additionally, we propose an efficient pre-training strategy that enhances performance even without ImageNet pre-training. |
| title | Segregation and Context Aggregation Network for Real-time Cloud Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.14178 |