解决合成到真实森林中树实例分割的标签粒度差异问题
Granularity-Aware Transfer for Tree Instance Segmentation in Synthetic and Real Forests
- 用细粒度合成数据教粗粒度真实数据，通过逻辑空间融合与掩码统一
- 小树和远距离树的分割准确率显著提升，整体掩码AP持续增长
- 适用于林业感知、遥感图像分析等需跨域迁移的场景
我们针对林业感知中合成到真实数据的迁移挑战，解决真实数据仅有粗粒度树标签而合成数据提供精细的树干/树冠标注的问题。构建了包含5.3万张合成图像和3600张真实图像的混合粒度数据集MGTD，提出四阶段协议分离领域偏移与粒度不匹配。核心贡献是粒度感知蒸馏，通过逻辑空间合并与掩码统一，将细粒度合成教师模型的结构先验迁移到粗标签学生模型。实验显示掩码平均精度（AP）持续提升，尤其在小树和远距离树上表现突出，为标签粒度受限下的仿真-真实迁移建立了基准测试平台。
原文摘要 · Abstract (English)
We address the challenge of synthetic-to-real transfer in forestry perception where real data have only coarse Tree labels while synthetic data provide fine-grained trunk/crown annotations. We introduce MGTD, a mixed-granularity dataset with 53k synthetic and 3.6k real images, and a four-stage protocol isolating domain shift and granularity mismatch. Our core contribution is granularity-aware distillation, which transfers structural priors from fine-grained synthetic teachers to a coarse-label student via logit-space merging and mask unification. Experiments show consistent mask AP gains, especially for small/distant trees, establishing a testbed for Sim-Real transfer under label granularity constraints.
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。