Dual Atrous Separable Convolution for Improving Agricultural Semantic Segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ling, Chee Mei, Akilan, Thangarajah, Phalke, Aparna Ravinda
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909664578371584
author Ling, Chee Mei
Akilan, Thangarajah
Phalke, Aparna Ravinda
author_facet Ling, Chee Mei
Akilan, Thangarajah
Phalke, Aparna Ravinda
contents Agricultural image semantic segmentation is a pivotal component of modern agriculture, facilitating accurate visual data analysis to improve crop management, optimize resource utilization, and boost overall productivity. This study proposes an efficient image segmentation method for precision agriculture, focusing on accurately delineating farmland anomalies to support informed decision-making and proactive interventions. A novel Dual Atrous Separable Convolution (DAS Conv) module is integrated within the DeepLabV3-based segmentation framework. The DAS Conv module is meticulously designed to achieve an optimal balance between dilation rates and padding size, thereby enhancing model performance without compromising efficiency. The study also incorporates a strategic skip connection from an optimal stage in the encoder to the decoder to bolster the model's capacity to capture fine-grained spatial features. Despite its lower computational complexity, the proposed model outperforms its baseline and achieves performance comparable to highly complex transformer-based state-of-the-art (SOTA) models on the Agriculture Vision benchmark dataset. It achieves more than 66% improvement in efficiency when considering the trade-off between model complexity and performance, compared to the SOTA model. This study highlights an efficient and effective solution for improving semantic segmentation in remote sensing applications, offering a computationally lightweight model capable of high-quality performance in agricultural imagery.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22570
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dual Atrous Separable Convolution for Improving Agricultural Semantic Segmentation
Ling, Chee Mei
Akilan, Thangarajah
Phalke, Aparna Ravinda
Computer Vision and Pattern Recognition
Agricultural image semantic segmentation is a pivotal component of modern agriculture, facilitating accurate visual data analysis to improve crop management, optimize resource utilization, and boost overall productivity. This study proposes an efficient image segmentation method for precision agriculture, focusing on accurately delineating farmland anomalies to support informed decision-making and proactive interventions. A novel Dual Atrous Separable Convolution (DAS Conv) module is integrated within the DeepLabV3-based segmentation framework. The DAS Conv module is meticulously designed to achieve an optimal balance between dilation rates and padding size, thereby enhancing model performance without compromising efficiency. The study also incorporates a strategic skip connection from an optimal stage in the encoder to the decoder to bolster the model's capacity to capture fine-grained spatial features. Despite its lower computational complexity, the proposed model outperforms its baseline and achieves performance comparable to highly complex transformer-based state-of-the-art (SOTA) models on the Agriculture Vision benchmark dataset. It achieves more than 66% improvement in efficiency when considering the trade-off between model complexity and performance, compared to the SOTA model. This study highlights an efficient and effective solution for improving semantic segmentation in remote sensing applications, offering a computationally lightweight model capable of high-quality performance in agricultural imagery.
title Dual Atrous Separable Convolution for Improving Agricultural Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.22570