Metraipolis › archive › dc_5afa5e2b6d4f
AlphaRAD: Grounded Zero-Shot Classification in Chest Radiology via $α$-Corrected Binary Cross Entropy and Factorized Latent Supervision — arXiv:2609.01757
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01757
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:49:42.003Z
- SHA-256 of the archived text
4ab5cee5d0ac564c8c22457af713aaf4ee2068fcaea01d49c0f3e529bbe34ecd- Stable URL of this page
https://metraipolis.com/documento/dc_5afa5e2b6d4f
How to cite
AlphaRAD: Grounded Zero-Shot Classification in Chest Radiology via $α$-Corrected Binary Cross Entropy and Factorized Latent Supervision — arXiv:2609.01757 — arXiv (en), https://arxiv.org/abs/2609.01757 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5afa5e2b6d4f (Metraipolis archive dc_5afa5e2b6d4f, sha256 4ab5cee5d0ac564c8c22457af713aaf4ee2068fcaea01d49c0f3e529bbe34ecd)
BibTeX
@misc{dc5afa5e2b6d4f,
title = {AlphaRAD: Grounded Zero-Shot Classification in Chest Radiology via $α$-Corrected Binary Cross Entropy and Factorized Latent Supervision — arXiv:2609.01757},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01757},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5afa5e2b6d4f; sha256 4ab5cee5d0ac564c8c22457af713aaf4ee2068fcaea01d49c0f3e529bbe34ecd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01757. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language Pretrained Models (VLPMs) offer a scalable path to open-vocabulary chest radiology understanding, yet two aspects remain underexplored: how structured clinical semantics extracted from medical reports can reduce in-batch noise during contrastive learning, and how cross-modal fusion can be designed to produce more faithful spatial grounding without added complexity. We introduce AlphaRAD, addressing these opportunities through two contributions. First, we construct a large-scale structured medical concept space from medical reports parsed by a Large Language Model for training, thereby mitigating in-batch learning noise and removing heuristic pair matching in contrastive learning, and thus naturally positioning AlphaRAD as a medical concept discriminator trained via $\alpha$-Corrected Binary Cross-Entropy. Second, we propose FLaS (Factorized Latent Supervision), an extremely simple yet effective cross-modal feature fusion module that factorizes VLPM representations into independent subspaces, using dedicated alignment supervision to enhance the expressiveness of spatial grounding without introducing additional model parameters. Through extensive empirical validation, AlphaRAD shows strong zero-shot generalization across diverse chest radiology tasks. Notably, it establishes state-of-the-art average performance across 16 classification benchmarks, while achieving individual state-of-the-art results via distinct gains on 7 grounding/phrase grounding and 3 segmentation datasets. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.01757 — 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 2026-10-17T05:25:58.012Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).