# Granularity-Aware Transfer for Tree Instance Segmentation in Synthetic and Real Forests

arXiv: https://arxiv.org/abs/2604.13722 · HTML: https://mlsanity.com/paper/2604.13722/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://mlsanity.com/paper/2007.08702/) (2020)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [RELLIS-3D Dataset: Data, Benchmarks and Analysis](https://mlsanity.com/paper/2011.12954/) (2020)
- [Maximum-Entropy Fine-Grained Classification](https://mlsanity.com/paper/1809.05934/) (2018)
- [FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees](https://mlsanity.com/paper/2309.01279/) (2023)
- [FinnWoodlands Dataset](https://mlsanity.com/paper/2304.00793/) (2023)
- [TimberVision: A Multi-Task Dataset and Framework for Log-Component Segmentation and Tracking in Autonomous Forestry Operations](https://mlsanity.com/paper/2501.07360/) (2025)
- [Training Deep Learning Algorithms on Synthetic Forest Images for Tree Detection](https://mlsanity.com/paper/2210.04104/) (2022)

## Abstract (arXiv)

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.