Pseudo-Label Refinement for Robust Wheat Head Segmentation via Two-Stage Hybrid Training

Abstract

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.

arXiv comment3 pages,3 figures, Extended abstract submitted to the 10th Computer Vision in Plant Phenotyping and Agriculture (CVPPA) Workshop, held in conjunction with ICCV 2025