Research
Granularity-Aware Transfer for Tree Instance Segmentation in Synthetic and Real Forests
arXiv:2604.13722v1 Announce Type: new Abstract: We address the challenge of synthetic-to-real transfer in forestry perception where real data have only coarse Tree labels while synthetic data provide
arXiv:2604.13722v1 Announce Type: new Abstract: 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.
Related
- Do Instance Priors Help Weakly Supervised Semantic Segmentation?
- Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift
- OpenTrack3D: Towards Accurate and Generalizable Open-Vocabulary 3D Instance Segmentation
- ReaLiTy and LADS: A Unified Framework and Dataset Suite for LiDAR Adaptation Across Sensors and Adverse Weather Conditions
- Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow
Source: arXiv cs.CV | 2026-04-16