Metraipolis › archive › dc_16c40258ce75

SciQNet: Two-Stage Multimodal Adaptation for Scientific Image Quality Assessment — arXiv:2608.05691

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05691
License (as archived)
CC0-1.0
Archived
2026-10-31T10:36:06.028Z
SHA-256 of the archived text
2a2e6ef29defd8188acad0f37addcd755e4264ece82187c145cc837ce241f7aa
Stable URL of this page
https://metraipolis.com/documento/dc_16c40258ce75

How to cite

SciQNet: Two-Stage Multimodal Adaptation for Scientific Image Quality Assessment — arXiv:2608.05691 — arXiv (en), https://arxiv.org/abs/2608.05691 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_16c40258ce75 (Metraipolis archive dc_16c40258ce75, sha256 2a2e6ef29defd8188acad0f37addcd755e4264ece82187c145cc837ce241f7aa)
BibTeX
@misc{dc16c40258ce75,
  title = {SciQNet: Two-Stage Multimodal Adaptation for Scientific Image Quality Assessment — arXiv:2608.05691},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05691},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_16c40258ce75; sha256 2a2e6ef29defd8188acad0f37addcd755e4264ece82187c145cc837ce241f7aa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05691. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific images are essential for communicating experimental observations, quantitative evidence and conceptual knowledge. Unlike natural images, their quality depends on both visual clarity and scientific informativeness, making assessment challenging. In this work, we present SciQNet, a two-stage multimodal adaptation framework for scientific image quality assessment. The first stage performs domain-adaptive pretraining on scientific document images and the second stage conducts task-specific fine-tuning with joint scoring and understanding supervision. For scoring-oriented supervision, we combine instruction tuning with a Huber loss derived from rating-word logits, while understanding-oriented supervision is formulated as multiple-choice visual question answering. Experiments show that using a 40% stratified subset of the domain-adaptive data gives the best performance among the evaluated pretraining fractions, suggesting that pretraining-data relevance may be as important as pretraining-data scale. The final model achieves an SIQA-S score of 92.21, an SIQA-U score of 47.38 and a combined score of 69.80. This work presents our solution to the ICME 2026 Scientific Image Quality Assessment Challenge, which ranked 2nd in the scoring track.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.05691 — 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 2026-10-31T10:23:30.997Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).