EUVIMEDEUVIMED entdecken
Crossref

Regression over Classification: Assessing Image Aesthetics via Multimodal Large Language Models

Xingyuan Ma, Shuai He, Anlong Ming, Haobin Zhong, Huadong Ma

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (10) · 7827-7835

DOI: 10.1609/aaai.v40i10.37726 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xingyuan Ma und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image Aesthetics Assessment (IAA) evaluates visual quality through user-centered perceptual analysis and can guide various applications. Recent advances in Multimodal Large Language Models (MLLMs) have sparked interest in adapting them for IAA. However, two critical limitations persist in applying MLLMs to IAA: 1) the tokenization strategy leads to insensitivity to scores, and 2) the classification-based decoding mechanisms introduce score quantization errors. Current MLLM-based IAA methods treat the task as coarse rating classification followed by probability-to-score mapping, which loses fine-grained information. To address these challenges, we propose ROC4MLLM, offering complementary solutions from two perspectives:1) Representation: We separate scores from the word token space to avoid tokenizing scores as text. An independent position token bridges these spaces, improving the sensitivity of the model to score positions in text. 2) Computation: We apply distinct loss functions for text and score predictions to enhance the sensitivity of the model to score gradients. Decoupling scores from text ensures effective supervision while preventing interference between scores and text in the loss computation. Extensive experiments across five datasets demonstrate that ROC4MLLM achieves state-of-the-art performance without requiring additional training data. Additionally, its plug-and-play design ensures seamless integration with existing MLLMs, boosting their IAA performance.

Zitieren

APA

Ma, X., He, S., Ming, A., Zhong, H., & Ma, H. (2026). Regression over Classification: Assessing Image Aesthetics via Multimodal Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(10), 7827-7835. https://doi.org/10.1609/aaai.v40i10.37726

Vancouver

Ma X, He S, Ming A, Zhong H, Ma H. Regression over Classification: Assessing Image Aesthetics via Multimodal Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(10):7827-7835. doi:10.1609/aaai.v40i10.37726

BibTeX
@article{Ma2026,
  author = {Ma, Xingyuan and He, Shuai and Ming, Anlong and Zhong, Haobin and Ma, Huadong},
  title = {Regression over Classification: Assessing Image Aesthetics via Multimodal Large Language Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {10},
  pages = {7827--7835},
  doi = {10.1609/aaai.v40i10.37726}
}
Kostenlos starten →