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

2026-04-15 · Pankaj Deoli, Atef Tej, Anmol Ashri, Anandatirtha JS, Karsten Berns 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.

📄 PDF Abstract BibTeX arXiv:2604.13722

Code (0)

등록된 구현이 없습니다.

Tasks

Instance Segmentation

SAPNet++: Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awareness

2026-02-25 · Zhaoyang Wei, Xumeng Han, Xuehui Yu, Xue Yang 외 arxiv

Single-point annotation is increasingly prominent in visual tasks for labeling cost reduction. However, it challenges tasks requiring high precision, such as the point-prompted instance segmentation (PPIS) task, which ai…

Multiple Instance Learning Instance Segmentation

Binary Tree based Chinese Word Segmentation

2013-05-17 · Kaixu Zhang, Can Wang, Maosong Sun

Chinese word segmentation is a fundamental task for Chinese language processing. The granularity mismatch problem is the main cause of the errors. This paper showed that the binary tree representation can store outputs w…

Chinese Word Segmentation Segmentation

FG-TreeSeg: Flow-Guided Tree Crown Segmentation without Instance Annotations

2026-01-31 · Pengyu Chen, Fangzheng Lyu, Sicheng Wang, Cuizhen Wang arxiv

Individual tree crown segmentation is an important task in remote sensing for forest biomass estimation and ecological monitoring. However, accurate delineation in dense, overlapping canopies remains a bottleneck. While …

Instance Segmentation

Segment Any Events with Language

2026-01-30 · Seungjun Lee, Gim Hee Lee arxiv

Scene understanding with free-form language has been widely explored within diverse modalities such as images, point clouds, and LiDAR. However, related studies on event sensors are scarce or narrowly centered on semanti…

Instance Segmentation Scene Understanding Event Segmentation Point Clouds

SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests

2026-06-06 · Maciej Wielgosz, Stefano Puliti, Rasmus Astrup arxiv

We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds. The model combines a serialization-based Point Transformer v3 backbone with a lightwei…

Domain Generalization Instance Segmentation Point Clouds