# Taking it further: leveraging pseudo labels for field delineation across label-scarce smallholder regions

arXiv: https://arxiv.org/abs/2312.08384 · HTML: https://mlsanity.com/paper/2312.08384/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 53 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Builds on (most cited first, 9 of 9)

- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [Instance Adaptive Self-Training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2008.12197/) (2020)
- [Unsupervised Domain Adaptation in Semantic Segmentation: a Review](https://mlsanity.com/paper/2005.10876/) (2020)
- [Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation](https://mlsanity.com/paper/2107.11279/) (2021)
- [Deep learning on edge: extracting field boundaries from satellite images with a convolutional neural network](https://mlsanity.com/paper/1910.12023/) (2019)
- [Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training](https://mlsanity.com/paper/1810.07911/) (2018)
- [Unlocking large-scale crop field delineation in smallholder farming systems with transfer learning and weak supervision](https://mlsanity.com/paper/2201.04771/) (2022)
- [Mapping smallholder cashew plantations to inform sustainable tree crop expansion in Benin](https://mlsanity.com/paper/2301.00363/) (2023)

## Built on by (most cited first, 2 of 2)

- [Responsible AI for Earth Observation](https://mlsanity.com/paper/2405.20868/) (2024)
- [Fields of The World: A Field Guide for Extracting Agricultural Field Boundaries](https://mlsanity.com/paper/2602.08131/) (2026)

## Abstract (arXiv)

Transfer learning allows for resource-efficient geographic transfer of pre-trained field delineation models. However, the scarcity of labeled data for complex and dynamic smallholder landscapes, particularly in Sub-Saharan Africa, remains a major bottleneck for large-area field delineation. This study explores opportunities of using sparse field delineation pseudo labels for fine-tuning models across geographies and sensor characteristics. We build on a FracTAL ResUNet trained for crop field delineation in India (median field size of 0.24 ha) and use this pre-trained model to generate pseudo labels in Mozambique (median field size of 0.06 ha). We designed multiple pseudo label selection strategies and compared the quantities, area properties, seasonal distribution, and spatial agreement of the pseudo labels against human-annotated training labels (n = 1,512). We then used the human-annotated labels and the pseudo labels for model fine-tuning and compared predictions against human field annotations (n = 2,199). Our results indicate i) a good baseline performance of the pre-trained model in both field delineation and field size estimation, and ii) the added value of regional fine-tuning with performance improvements in nearly all experiments. Moreover, we found iii) substantial performance increases when using only pseudo labels (up to 77% of the IoU increases and 68% of the RMSE decreases obtained by human labels), and iv) additional performance increases when complementing human annotations with pseudo labels. Pseudo labels can be efficiently generated at scale and thus facilitate domain adaptation in label-scarce settings. The workflow presented here is a stepping stone for overcoming the persisting data gaps in heterogeneous smallholder agriculture of Sub-Saharan Africa, where labels are commonly scarce.