Metraipolis › archive › dc_ad5c8543c745

Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding — arXiv:2609.30682

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30682
License (as archived)
CC0-1.0
Archived
2026-10-08T03:12:30.306Z
SHA-256 of the archived text
449ed5e697780aa2eb68267fd2a6e82ca22992fb249d740eb905537544f56fc7
Stable URL of this page
https://metraipolis.com/documento/dc_ad5c8543c745

How to cite

Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding — arXiv:2609.30682 — arXiv (en), https://arxiv.org/abs/2609.30682 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ad5c8543c745 (Metraipolis archive dc_ad5c8543c745, sha256 449ed5e697780aa2eb68267fd2a6e82ca22992fb249d740eb905537544f56fc7)
BibTeX
@misc{dcad5c8543c745,
  title = {Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding — arXiv:2609.30682},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30682},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ad5c8543c745; sha256 449ed5e697780aa2eb68267fd2a6e82ca22992fb249d740eb905537544f56fc7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30682. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-supervised pre-training with Vision Transformers, including Masked Autoencoders (MAE), is difficult to apply to gigapixel scientific images. Random masking is poorly matched to the structured, multi-scale morphology of scientific data, while uniform tokenization produces prohibitively long sequences that make $O(N^2)$ attention impractical. We propose SGMA, a structure-guided masked autoencoding framework for ultra-high-resolution scientific images. SGMA couples two components: a content-adaptive quadtree tokenizer that compresses gigapixel images into a fixed-length sequence, and a structure-conditioned masking process that biases reconstruction toward spatially informative regions. To stabilize this process across scales, we introduce Damped Accumulation (DA), which aggregates signal-dependent responses across the tree into a structure canvas used to guide masking. The resulting pre-training task preserves fine microstructure while remaining compatible with standard ViT encoders and MAE-style reconstruction. Across electron microscopy, whole-slide optical microscopy, and X-ray CT datasets, SGMA consistently outperforms MAE baselines. It achieves 95.68% Dice on the 8K x 8K x 28K SpringXCT dataset, improving over the same-architecture MAE baseline by +13.00 points, and 83.21% Dice on the 32K^2 WSI PAIP dataset, improving by +16.84 points, while providing up to a 24.8x inference speedup.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.30682 — 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 2026-10-08T02:50:19.034Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).