Semi-Supervised Weed Detection for Rapid Deployment and Enhanced Efficiency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Saleh, Alzayat, Olsen, Alex, Wood, Jake, Philippa, Bronson, Azghadi, Mostafa Rahimi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910444155830272
author Saleh, Alzayat
Olsen, Alex
Wood, Jake
Philippa, Bronson
Azghadi, Mostafa Rahimi
author_facet Saleh, Alzayat
Olsen, Alex
Wood, Jake
Philippa, Bronson
Azghadi, Mostafa Rahimi
contents Weeds present a significant challenge in agriculture, causing yield loss and requiring expensive control measures. Automatic weed detection using computer vision and deep learning offers a promising solution. However, conventional deep learning methods often require large amounts of labelled training data, which can be costly and time-consuming to acquire. This paper introduces a novel method for semi-supervised weed detection, comprising two main components. Firstly, a multi-scale feature representation technique is employed to capture distinctive weed features across different scales. Secondly, we propose an adaptive pseudo-label assignment strategy, leveraging a small set of labelled images during training. This strategy dynamically assigns confidence scores to pseudo-labels generated from unlabeled data. Additionally, our approach integrates epoch-corresponding and mixed pseudo-labels to further enhance the learning process. Experimental results on the COCO dataset and five prominent weed datasets -- CottonWeedDet12, CropAndWeed, Palmer amaranth, RadishWheat, and RoboWeedMap -- illustrate that our method achieves state-of-the-art performance in weed detection, even with significantly less labelled data compared to existing techniques. This approach holds the potential to alleviate the labelling burden and enhance the feasibility and deployment speed of deep learning for weed detection in real-world agricultural scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2405_07399
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Semi-Supervised Weed Detection for Rapid Deployment and Enhanced Efficiency
Saleh, Alzayat
Olsen, Alex
Wood, Jake
Philippa, Bronson
Azghadi, Mostafa Rahimi
Computer Vision and Pattern Recognition
Weeds present a significant challenge in agriculture, causing yield loss and requiring expensive control measures. Automatic weed detection using computer vision and deep learning offers a promising solution. However, conventional deep learning methods often require large amounts of labelled training data, which can be costly and time-consuming to acquire. This paper introduces a novel method for semi-supervised weed detection, comprising two main components. Firstly, a multi-scale feature representation technique is employed to capture distinctive weed features across different scales. Secondly, we propose an adaptive pseudo-label assignment strategy, leveraging a small set of labelled images during training. This strategy dynamically assigns confidence scores to pseudo-labels generated from unlabeled data. Additionally, our approach integrates epoch-corresponding and mixed pseudo-labels to further enhance the learning process. Experimental results on the COCO dataset and five prominent weed datasets -- CottonWeedDet12, CropAndWeed, Palmer amaranth, RadishWheat, and RoboWeedMap -- illustrate that our method achieves state-of-the-art performance in weed detection, even with significantly less labelled data compared to existing techniques. This approach holds the potential to alleviate the labelling burden and enhance the feasibility and deployment speed of deep learning for weed detection in real-world agricultural scenarios.
title Semi-Supervised Weed Detection for Rapid Deployment and Enhanced Efficiency
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.07399