ReLeaf: Benchmarking Leaf Segmentation across Domains and Species

TL;DR

This paper benchmarks leaf segmentation models across multiple plant species and domains, introduces a new dataset, and evaluates model generalization for precision agriculture applications.

Contribution

It systematically compares modern segmentation architectures, identifies a best-performing model, and provides a new diverse leaf segmentation dataset for improved robustness.

Findings

YOLO26 offers the best trade-off for real-world leaf segmentation.

Models trained only on lab data perform poorly across different domains.

A new dataset with 23 plant species enhances generalization testing.

Abstract

Rising global food demand and growing climate pressure increase the need for sustainable, precise agricultural practices. Automated, individualized plant treatment relies on fine-grained visual analysis, yet leaf-level segmentation remains underexplored despite its value for assessing crop health, growth dynamics, yield potential and localized stress symptoms. Progress is limited by a lack of dedicated datasets, especially regarding species coverage, and by the absence of systematic evaluations of modern instance-segmentation architectures for this task. We address these gaps by surveying current data and identifying four suitable, publicly available leaf-segmentation datasets. Using them, we compare one-stage, two-stage and Transformer-based detectors and identify a YOLO26 model configuration to provide the best trade-off for real-world precision-agriculture tasks. Extensive cross-domain generalization experiments reveal substantial performance drops across plant species and recording setups, especially for models trained solely on laboratory data. To strengthen data availability, we introduce a new benchmark dataset with leaf-level masks for 23 plant species, created via semi-automatic annotation of selected CropAndWeed images. A model trained on all four existing datasets achieves a mean mAP50-95 of 83.9% across their corresponding test sets and 40.2% on our new benchmark, demonstrating improved generalization and highlighting the need for diverse leaf-segmentation datasets in robust precision agriculture.