DAS-SK: An Adaptive Model Integrating Dual Atrous Separable and Selective Kernel CNN for Agriculture Semantic Segmentation

2026-02-09

AI Summary

This work addresses the challenge of balancing accuracy and computational efficiency in high-resolution agricultural image semantic segmentation, which hinders deployment on edge devices. The authors propose DAS-SK, a lightweight architecture that integrates dual atrous separable convolution (DAS-Conv) and selective kernel convolution (SK-Conv) within an enhanced DeepLabV3 framework, while augmenting the ASPP module. Leveraging dual backbones—MobileNetV3-Large and EfficientNet-B3—the model effectively captures multi-scale local details and global contextual information. The approach achieves state-of-the-art performance on LandCover.ai, VDD, and PhenoBench benchmarks while significantly reducing model complexity, with up to 21× fewer parameters and 19× lower GFLOPs compared to advanced Transformer-based models, thus offering both high accuracy and computational efficiency.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

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.

Problem

• semantic segmentation
• agricultural imagery
• computational efficiency
• edge deployment
• multi-scale feature learning

Innovation

• Selective Kernel Convolution
• Dual Atrous Separable Convolution
• Lightweight Semantic Segmentation
• Agricultural Remote Sensing
• Efficient Deep Learning