Metraipolis › archive › dc_323d44dd2115

ProGuT: Label-Efficient Panoptic Segmentation for Forest Scenes — arXiv:2609.36891

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36891
License (as archived)
CC0-1.0
Archived
2026-10-07T18:38:38.039Z
SHA-256 of the archived text
a918f2abdf2a9a7741af166e65e720295271eb728eef8d0db14358ef92bacffa
Stable URL of this page
https://metraipolis.com/documento/dc_323d44dd2115

How to cite

ProGuT: Label-Efficient Panoptic Segmentation for Forest Scenes — arXiv:2609.36891 — arXiv (en), https://arxiv.org/abs/2609.36891 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_323d44dd2115 (Metraipolis archive dc_323d44dd2115, sha256 a918f2abdf2a9a7741af166e65e720295271eb728eef8d0db14358ef92bacffa)
BibTeX
@misc{dc323d44dd2115,
  title = {ProGuT: Label-Efficient Panoptic Segmentation for Forest Scenes — arXiv:2609.36891},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36891},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_323d44dd2115; sha256 a918f2abdf2a9a7741af166e65e720295271eb728eef8d0db14358ef92bacffa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36891. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Panoptic segmentation in forest environments is bottlenecked not by semantic quality but by instance separation; existing unsupervised panoptic approaches produce usable stuff maps but near-zero thing quality. Depth or flow-based instance discovery methods needs sensors that are not always available. We present ProGuT (Prototype Guided Training), which produces panoptic pseudo-labels without per-image training masks, needing only unlabeled images and one-time cluster-to-class mapping. ProGuT clusters CLIP patch features, then recovers trunk instances through multiscale geometric prior that falsifies non-trunk structures via structure-tensor. This is cheap compared to depth, flow or class-supervision methods to create pseudo labels. These are then used for downstream tasks which we evaluate against other unsupervised baselines. ProGuT achieves a Panoptic Quality (PQ) of 65.2 on Our-forest dataset (2.6x improvement over the initial pseudo-label quality) and reaches 65.9 mIoU on Freiburg Forest, outperforming unsupervised baselines like PiCIE (45.3 IoU) and STEGO(57.6IoU). Additionally, ProGuT outperforms existing unsupervised methods for class-agnostic trunk instance benchmark.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.36891 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T18:04:24.772Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).