Metraipolis › archive › dc_8cd04b080cb4

SlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling — arXiv:2609.00396

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00396
License (as archived): CC0-1.0
Archived: 2026-10-17T07:10:27.918Z
SHA-256 of the archived text: 206456ef7a93b36240567380f7982a1c5b2477f6cbbbab1d93e195d746ecabc8
Stable URL of this page: https://metraipolis.com/documento/dc_8cd04b080cb4

How to cite

SlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling — arXiv:2609.00396 — arXiv (en), https://arxiv.org/abs/2609.00396 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8cd04b080cb4 (Metraipolis archive dc_8cd04b080cb4, sha256 206456ef7a93b36240567380f7982a1c5b2477f6cbbbab1d93e195d746ecabc8)

BibTeX

@misc{dc8cd04b080cb4,
  title = {SlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling — arXiv:2609.00396},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00396},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8cd04b080cb4; sha256 206456ef7a93b36240567380f7982a1c5b2477f6cbbbab1d93e195d746ecabc8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00396. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Histopathological whole slide images (WSIs) are central to cancer diagnosis, but their gigapixel scale, tissue heterogeneity, weak slide-level supervision, sparse diagnostic regions, and multi-scale evidence make robust automated analysis challenging. Multiple instance learning (MIL) is widely used to aggregate tile-level features into slide-level predictions, yet existing augmentation strategies often perturb tissue regions without preserving diagnostic relevance, slide context, or cross-scale structure. We propose SlideMix, a model-agnostic multimodal augmentation framework for MIL-based WSI analysis. SlideMix uses a retrieval-augmented vision-language model (VLM)-based Visual-Language Adaptive Region selector to identify diagnostically relevant regions and reduce weak-label noise. It then performs In-place Tile Shuffling within meaningful tissue regions to mix feature embeddings while preserving slide-level context. A VLM-based soft-labeling module supervises mixed samples, while a multi-factor, loss-driven online Curriculum-Learning Feedback scheme adaptively controls shuffle granularity, feature similarity, and shuffle ratio to promote cross-scale representation learning. Across 11 WSI datasets comprising 20,523 slides, 8 diagnostic tasks, and 10 WSI backbones, SlideMix improves accuracy and generalization in most settings and compares favorably with established augmentation baselines, providing a simple plug-and-play approach for more robust and scalable digital pathology models. Source code: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.00396 — 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 2026-10-17T07:00:58.901Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).