Adapting Vision-Language Models Without Labels: A Comprehensive Survey
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918117411651584 |
|---|---|
| author | Dong, Hao Sheng, Lijun Liang, Jian He, Ran Chatzi, Eleni Fink, Olga |
| author_facet | Dong, Hao Sheng, Lijun Liang, Jian He, Ran Chatzi, Eleni Fink, Olga |
| contents | Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when directly applied to specific downstream scenarios without task-specific adaptation. To enhance their utility while preserving data efficiency, recent research has increasingly focused on unsupervised adaptation methods that do not rely on labeled data. Despite the growing interest in this area, there remains a lack of a unified, task-oriented survey dedicated to unsupervised VLM adaptation. To bridge this gap, we present a comprehensive and structured overview of the field. We propose a taxonomy based on the availability and nature of unlabeled visual data, categorizing existing approaches into four key paradigms: Data-Free Transfer (no data), Unsupervised Domain Transfer (abundant data), Episodic Test-Time Adaptation (batch data), and Online Test-Time Adaptation (streaming data). Within this framework, we analyze core methodologies and adaptation strategies associated with each paradigm, aiming to establish a systematic understanding of the field. Additionally, we review representative benchmarks across diverse applications and highlight open challenges and promising directions for future research. An actively maintained repository of relevant literature is available at https://github.com/tim-learn/Awesome-LabelFree-VLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05547 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adapting Vision-Language Models Without Labels: A Comprehensive Survey Dong, Hao Sheng, Lijun Liang, Jian He, Ran Chatzi, Eleni Fink, Olga Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when directly applied to specific downstream scenarios without task-specific adaptation. To enhance their utility while preserving data efficiency, recent research has increasingly focused on unsupervised adaptation methods that do not rely on labeled data. Despite the growing interest in this area, there remains a lack of a unified, task-oriented survey dedicated to unsupervised VLM adaptation. To bridge this gap, we present a comprehensive and structured overview of the field. We propose a taxonomy based on the availability and nature of unlabeled visual data, categorizing existing approaches into four key paradigms: Data-Free Transfer (no data), Unsupervised Domain Transfer (abundant data), Episodic Test-Time Adaptation (batch data), and Online Test-Time Adaptation (streaming data). Within this framework, we analyze core methodologies and adaptation strategies associated with each paradigm, aiming to establish a systematic understanding of the field. Additionally, we review representative benchmarks across diverse applications and highlight open challenges and promising directions for future research. An actively maintained repository of relevant literature is available at https://github.com/tim-learn/Awesome-LabelFree-VLMs. |
| title | Adapting Vision-Language Models Without Labels: A Comprehensive Survey |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.05547 |