The Effects of Synthetic Data and Label Distribution on Canola Branch Counting
For agricultural phenotyping researchers, this work provides practical guidelines on using synthetic data to reduce annotation costs, though the findings are incremental and domain-specific.
The paper investigates how synthetic-to-real image ratio and synthetic label distribution affect canola branch counting. The best ratio (1:7) reduces mean absolute difference by 7.6%, and Gaussian-smoothed real label distribution yields a 14.7% improvement over real-only training.
Collecting annotated plant images for automated phenotyping is often slow and expensive. Plant models simulating growth and development can generate unlimited synthetic images with exact labels. However, previous work has established that whether incorporating synthetic data improves performance depends on the ratio of synthetic to real images and the label distribution of the synthetic dataset. To systematically quantify both factors, we train ResNet-18 models on a canola branch-counting task using a calibrated L-system plant model. We vary each factor independently. Synthetic-to-real ratios of 1:5 to 1:22 broadly improve performance; the best ratio (1:7) reduces mean absolute difference by 7.6% over real-only training. For label distribution, a uniform synthetic distribution is strongly suboptimal (abs. diff. of approximately 1.70); interpolating 90% toward the real distribution yields abs. diff. 0.927, whereas Gaussian smoothing of the real label distribution yields the best overall result (abs. diff. 0.912, a 14.7% improvement over real-only). A minimum of 10 synthetic images per label offers a simpler alternative with modest gains, while 100 per label over-corrects and hurts performance.