Semi-Self-Supervised Domain Adaptation: Developing Deep Learning Models with Limited Annotated Data for Wheat Head Segmentation

TL;DR

This paper presents a semi-self-supervised domain adaptation method for wheat head segmentation that requires minimal manual annotation, leveraging a small set of labeled images and unannotated video data to achieve robust, generalizable deep learning models for precision agriculture.

Contribution

The authors introduce a novel semi-self-supervised domain adaptation approach using deep CNNs and probabilistic diffusion, significantly reducing annotation effort for agricultural image segmentation.

Findings

Achieved 80.7% Dice score on internal test data.

Achieved 64.8% Dice score on diverse external datasets.

Demonstrated potential for scalable, generalizable agricultural imaging solutions.

Abstract

Precision agriculture involves the application of advanced technologies to improve agricultural productivity, efficiency, and profitability while minimizing waste and environmental impact. Deep learning approaches enable automated decision-making for many visual tasks. However, in the agricultural domain, variability in growth stages and environmental conditions, such as weather and lighting, presents significant challenges to developing deep learning-based techniques that generalize across different conditions. The resource-intensive nature of creating extensive annotated datasets that capture these variabilities further hinders the widespread adoption of these approaches. To tackle these issues, we introduce a semi-self-supervised domain adaptation technique based on deep convolutional neural networks with a probabilistic diffusion process, requiring minimal manual data annotation. Using only three manually annotated images and a selection of video clips from wheat fields, we generated a large-scale computationally annotated dataset of image-mask pairs and a large dataset of unannotated images extracted from video frames. We developed a two-branch convolutional encoder-decoder model architecture that uses both synthesized image-mask pairs and unannotated images, enabling effective adaptation to real images. The proposed model achieved a Dice score of 80.7\% on an internal test dataset and a Dice score of 64.8\% on an external test set, composed of images from five countries and spanning 18 domains, indicating its potential to develop generalizable solutions that could encourage the wider adoption of advanced technologies in agriculture.