DAS-SK: An Adaptive Model Integrating Dual Atrous Separable and Selective Kernel CNN for Agriculture Semantic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910016277053440 |
|---|---|
| author | Chee, Mei Ling Akilan, Thangarajah Phalke, Aparna Ravindra Keisham, Kanchan |
| author_facet | Chee, Mei Ling Akilan, Thangarajah Phalke, Aparna Ravindra Keisham, Kanchan |
| contents | Semantic segmentation in high-resolution agricultural imagery demands models that strike a careful balance between accuracy and computational efficiency to enable deployment in practical systems. In this work, we propose DAS-SK, a novel lightweight architecture that retrofits selective kernel convolution (SK-Conv) into the dual atrous separable convolution (DAS-Conv) module to strengthen multi-scale feature learning. The model further enhances the atrous spatial pyramid pooling (ASPP) module, enabling the capture of fine-grained local structures alongside global contextual information. Built upon a modified DeepLabV3 framework with two complementary backbones - MobileNetV3-Large and EfficientNet-B3, the DAS-SK model mitigates limitations associated with large dataset requirements, limited spectral generalization, and the high computational cost that typically restricts deployment on UAVs and other edge devices. Comprehensive experiments across three benchmarks: LandCover.ai, VDD, and PhenoBench, demonstrate that DAS-SK consistently achieves state-of-the-art performance, while being more efficient than CNN-, transformer-, and hybrid-based competitors. Notably, DAS-SK requires up to 21x fewer parameters and 19x fewer GFLOPs than top-performing transformer models. These findings establish DAS-SK as a robust, efficient, and scalable solution for real-time agricultural robotics and high-resolution remote sensing, with strong potential for broader deployment in other vision domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08168 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DAS-SK: An Adaptive Model Integrating Dual Atrous Separable and Selective Kernel CNN for Agriculture Semantic Segmentation Chee, Mei Ling Akilan, Thangarajah Phalke, Aparna Ravindra Keisham, Kanchan Computer Vision and Pattern Recognition Semantic segmentation in high-resolution agricultural imagery demands models that strike a careful balance between accuracy and computational efficiency to enable deployment in practical systems. In this work, we propose DAS-SK, a novel lightweight architecture that retrofits selective kernel convolution (SK-Conv) into the dual atrous separable convolution (DAS-Conv) module to strengthen multi-scale feature learning. The model further enhances the atrous spatial pyramid pooling (ASPP) module, enabling the capture of fine-grained local structures alongside global contextual information. Built upon a modified DeepLabV3 framework with two complementary backbones - MobileNetV3-Large and EfficientNet-B3, the DAS-SK model mitigates limitations associated with large dataset requirements, limited spectral generalization, and the high computational cost that typically restricts deployment on UAVs and other edge devices. Comprehensive experiments across three benchmarks: LandCover.ai, VDD, and PhenoBench, demonstrate that DAS-SK consistently achieves state-of-the-art performance, while being more efficient than CNN-, transformer-, and hybrid-based competitors. Notably, DAS-SK requires up to 21x fewer parameters and 19x fewer GFLOPs than top-performing transformer models. These findings establish DAS-SK as a robust, efficient, and scalable solution for real-time agricultural robotics and high-resolution remote sensing, with strong potential for broader deployment in other vision domains. |
| title | DAS-SK: An Adaptive Model Integrating Dual Atrous Separable and Selective Kernel CNN for Agriculture Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.08168 |