Metraipolis › archive › dc_9b595f024f22

Scalable In-Domain Self-Supervised Foundation Model for Dense Representation Transfer in High-Resolution Plant Imaging — arXiv:2609.32183

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32183
License (as archived)
CC0-1.0
Archived
2026-10-07T23:50:46.118Z
SHA-256 of the archived text
4200a772a7dbd7852b578c0acfcbf2f2407f706d34464adda94a880ee076124e
Stable URL of this page
https://metraipolis.com/documento/dc_9b595f024f22

How to cite

Scalable In-Domain Self-Supervised Foundation Model for Dense Representation Transfer in High-Resolution Plant Imaging — arXiv:2609.32183 — arXiv (en), https://arxiv.org/abs/2609.32183 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9b595f024f22 (Metraipolis archive dc_9b595f024f22, sha256 4200a772a7dbd7852b578c0acfcbf2f2407f706d34464adda94a880ee076124e)
BibTeX
@misc{dc9b595f024f22,
  title = {Scalable In-Domain Self-Supervised Foundation Model for Dense Representation Transfer in High-Resolution Plant Imaging — arXiv:2609.32183},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32183},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9b595f024f22; sha256 4200a772a7dbd7852b578c0acfcbf2f2407f706d34464adda94a880ee076124e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32183. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-resolution plant imaging enables detailed characterization of plant morphology, but dense scientific analysis remains limited by costly pixel-level annotations, large image pixel dimensions, and substantial variation in imaging conditions. This work proposes a scalable in-domain self-supervised pretrained foundation model for high-resolution, high-pixel-dimension multi-species plant imagery. A masked autoencoder with a ViT backbone is pretrained on more than 10 million multi-view plant image tiles using distributed training. Following scalable pretraining, the learned foundation-model representations are comprehensively benchmarked across fine-grained dense prediction and coarse global feature recognition, with particular emphasis on limited supervision and realistic downstream imaging conditions. This work focuses on the domain gap of existing foundation models in dense feature representation and transfer. Through extensive experiments involving limited annotations, cross-view variation, and resolution degradation, the in-domain FM achieves a Mean Dice of 0.8686 and a Pooled Dice of 0.8959, outperforming an MAE counterpart pretrained on large-scale natural-image data by 0.0694 and 0.0613, respectively. The results further indicate that increasing pretraining scale produces consistent improvements in dense feature transfer. Overall, these findings suggest that scaling in-domain self-supervised pretraining can reduce the domain gap and improve transferable dense representations for high-pixel-dimension scientific imaging.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2609.32183 — 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 2026-10-07T23:29:26.979Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).