通过两阶段混合训练与伪标签优化，提升小麦穗分割鲁棒性
Pseudo-Label Refinement for Robust Wheat Head Segmentation via Two-Stage Hybrid Training
- 采用教师-学生迭代框架，逐步精化伪标签
- 在开发集和测试集上均取得优异分割性能
- 适合遥感图像语义分割任务的实战应用
本文介绍了我们在全球小麦全语义分割竞赛中的解决方案。我们构建了一个系统的自训练框架，结合两阶段混合训练策略与大规模数据增强。核心模型采用基于Mix Transformer（MiT-B4）骨干网络的SegFormer。通过迭代式教师-学生循环，持续优化模型精度并最大化数据利用率。该方法在开发集与测试阶段数据集上均表现出色，展现了良好的竞争性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。