Can Synthetic Data Overcome the Generalization Limits of AI-Based Flower and Pod Detection Across Cowpea Breeding Genotypes and Environments?

2026-07-30

AI Summary

This study addresses the significant degradation in generalization performance of cowpea flower and pod detection models across diverse genotypes and environments, compounded by the high cost of acquiring real annotated data. To overcome this challenge, the authors propose a synthetic data generation approach based on procedural 3D plant modeling. The method enhances photorealism through high dynamic range (HDR) linear image representation and camera imaging-aware rendering, while explicitly minimizing domain shift between synthetic and real data by optimizing their Wasserstein distance. Experimental results demonstrate that, when combined with as few as five real images, the proposed approach achieves or even surpasses the performance of models trained entirely on real data in spatial generalization tasks, yielding substantial improvements in pod detection mAP@50 under low-data regimes.

Abstract

High-throughput phenotyping requires AI-enabled computer vision models that generalize across genotypes, locations, and growing seasons, yet such models often lose accuracy under new conditions. Annotating real imagery for every genotype-by-environment (G x E) combination a breeding program encounters is prohibitively expensive. We quantify how G x E shifts affect AI-based detection of cowpea flowers and pods across two California locations and two growing seasons. Flower detection mAP@50 fell from 76.3% to as low as 50.6% under unseen shifts, and pod detection was more sensitive. Feature-space and image-quality diagnostics confirmed these losses track measurable distributional shifts. Because closing this gap with real data alone is not practical, we test whether synthetic imagery, rendered from a procedural 3D cowpea model, can substitute for that annotation burden. Synthetic supervision alone improved over pretraining but remained limited by a domain gap driven by camera image formation, not scene content. A domain-gap-aware camera-realism augmentation strategy, optimized against measured real-image statistics via Wasserstein distance, narrowed this gap, and a linear HDR representation converted a smaller measured gap into a larger detection gain than an 8-bit representation. Optimized HDR synthetic data combined with as few as five real images matched or exceeded the real-data baseline for spatial generalization, and pod detection benefited most at the lowest shot counts, with more modest gains under temporal shift. These results show that synthetic data can overcome the generalization limits of AI-based flower and pod detection, but only when the domain gap is measured and optimized rather than assumed away.

Problem

• generalization
• synthetic data
• phenotyping
• domain gap
• cowpea

Innovation

• synthetic data
• domain gap
• HDR representation
• procedural 3D modeling
• Wasserstein distance