EUVIMEDEUVIMED entdecken
Crossref

Generalizing Vision-Language Models to Novel Domains: A Comprehensive Survey

Xinyao Li, Jingjing Li, Fengling Li, Lei Zhu, Yang Yang, Heng Tao Shen

ACM Transactions on Multimedia Computing, Communications, and Applications · 04.06.2026

DOI: 10.1145/3816251 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 04.06.2026. Verfasst von Xinyao Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 215 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, vision-language pretraining has emerged as a transformative technique that integrates the strengths of both visual and textual modalities, resulting in powerful vision-language models (VLMs). Leveraging web-scale pretraining data, these models exhibit strong zero-shot capabilities. However, their performance often deteriorates when confronted with domain-specific or specialized generalization tasks. To address this, a growing body of research focuses on transferring or generalizing the rich knowledge embedded in VLMs to various downstream applications. This survey aims to comprehensively summarize the generalization settings, methodologies, benchmarking and results in VLM literatures. Delving into the typical VLM structures, current literatures are categorized into prompt-based , parameter-based and feature-based methods according to the transferred modules. The differences and characteristics in each category are furthered summarized and discussed by revisiting the typical transfer learning (TL) settings , providing novel interpretations for TL in the era of VLMs. Popular benchmarks for VLM generalization are further introduced with thorough performance comparisons among the reviewed methods. Following the advances in large-scale generalizable pretraining, this survey also discusses the relations and differences between VLMs and up-to-date multimodal large language models (MLLM), e.g., DeepSeek-VL. By systematically reviewing the surging literatures in vision-language research from a novel and practical generalization prospective, this survey contributes to a clear landscape of current and future multimodal researches.

Zitieren

APA

Li, X., Li, J., Li, F., Zhu, L., Yang, Y., & Shen, H. T. (2026). Generalizing Vision-Language Models to Novel Domains: A Comprehensive Survey. ACM Transactions on Multimedia Computing, Communications, and Applications. https://doi.org/10.1145/3816251

Vancouver

Li X, Li J, Li F, Zhu L, Yang Y, Shen HT. Generalizing Vision-Language Models to Novel Domains: A Comprehensive Survey. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026. doi:10.1145/3816251

BibTeX
@article{Li2026,
  author = {Li, Xinyao and Li, Jingjing and Li, Fengling and Zhu, Lei and Yang, Yang and Shen, Heng Tao},
  title = {Generalizing Vision-Language Models to Novel Domains: A Comprehensive Survey},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2026},
  doi = {10.1145/3816251}
}
Kostenlos starten →