Metraipolis › archive › dc_ff8f5ad33870

Extending Decoupled Attention to Dense Prediction and Masked Training for Multi-Channel Images — arXiv:2609.21629

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21629
License (as archived)
CC0-1.0
Archived
2026-10-10T02:29:38.422Z
SHA-256 of the archived text
8052a5e3e204c5a724ad0c0d9a894ee8e7ccc66ab2d10cfd1fa9eba203845ce0
Stable URL of this page
https://metraipolis.com/documento/dc_ff8f5ad33870

How to cite

Extending Decoupled Attention to Dense Prediction and Masked Training for Multi-Channel Images — arXiv:2609.21629 — arXiv (en), https://arxiv.org/abs/2609.21629 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff8f5ad33870 (Metraipolis archive dc_ff8f5ad33870, sha256 8052a5e3e204c5a724ad0c0d9a894ee8e7ccc66ab2d10cfd1fa9eba203845ce0)
BibTeX
@misc{dcff8f5ad33870,
  title = {Extending Decoupled Attention to Dense Prediction and Masked Training for Multi-Channel Images — arXiv:2609.21629},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21629},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff8f5ad33870; sha256 8052a5e3e204c5a724ad0c0d9a894ee8e7ccc66ab2d10cfd1fa9eba203845ce0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21629. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-Channel imaging (MCI) data differs fundamentally from natural images, as each channel records a semantically distinct signal rather than a colour band. To adapt vision encoders to MCI data, Multi-Channel Vision Transformers (MC-ViTs) tokenize each channel independently and concatenate the resulting tokens into one sequence, and the channel count is no longer fixed by the architecture. Self-attention is then computed across all channel-patch tokens with no restriction on which channels attend to which, which dilutes the features of individual channels. The Decoupled Vision Transformer (DC-ViT) regulates this by separating updates computed within a channel from updates computed across channels, and by forming a representation per channel before the channels are combined. Its formulation, however, pairs tokens by spatial position, and thus requires the same visible tokens in every channel. Correspondence under independent per-channel masking is recovered by solving a linear assignment between the retained patches of each channel, which allows decoupled attention to be combined with current masked multi-channel training in its standard configuration rather than a restricted one. Across three classification and three segmentation benchmarks spanning fluorescence microscopy, imaging mass cytometry and satellite imaging, including dense prediction at high channel counts, the resulting formulation outperforms the strongest MC-ViT baseline.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.21629 — 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 2026-10-10T02:07:36.084Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).