This extended abstract details our solution for the Global Wheat Full Semantic Segmentation Competition. We developed a systematic self-training framework. This framework combines a two-stage hybrid training strategy with extensive data augmentation. Our core model is SegFormer with a Mix Transformer (MiT-B4) backbone. We employ an iterative teacher-student loop. This loop progressively refines model accuracy. It also maximizes data utilization. Our method achieved competitive performance. This was evident on both the Development and Testing Phase datasets.
Cite
@article{arxiv.2512.11874,
title = {Pseudo-Label Refinement for Robust Wheat Head Segmentation via Two-Stage Hybrid Training},
author = {Jiahao Jiang and Zhangrui Yang and Xuanhan Wang and Jingkuan Song},
journal= {arXiv preprint arXiv:2512.11874},
year = {2025}
}
Comments
3 pages,3 figures, Extended abstract submitted to the 10th Computer Vision in Plant Phenotyping and Agriculture (CVPPA) Workshop, held in conjunction with ICCV 2025