关于对比式视觉-语言模型的领域鲁棒性
On the Domain Robustness of Contrastive Vision-Language Models
AI总结：
提出Deepbench框架，利用LLM生成领域定制图像损坏以评估对比式视觉-语言模型在六类真实场景中的鲁棒性差异，发现模型在领域偏移下性能显著波动，强调需针对性评估。
摘要：
在实际的视觉-语言应用中，从业者越来越依赖大型预训练基础模型而非定制解决方案，尽管其训练数据和过程的透明度有限。虽然这些模型在通用基准上表现优异，但在特定领域偏移（如独特成像条件或环境变化）下，其性能可能显著下降。本研究提出Deepbench框架，用于评估视觉-语言模型（VLMs）的领域特定鲁棒性。Deepbench利用大型语言模型（LLM）生成针对特定部署领域定制的现实场景、上下文感知的图像损坏，无需标注数据。我们在六个真实领域评估了多种对比式视觉-语言架构及其变体，观察到鲁棒性存在显著差异，凸显了开展针对性领域感知评估的必要性。Deepbench已作为开源软件发布，以支持领域感知鲁棒性评估的进一步研究。
英文摘要：
In real-world vision-language applications, practitioners increasingly rely on large, pretrained foundation models rather than custom-built solutions, despite limited transparency regarding their training data and processes. While these models achieve impressive performance on general benchmarks, their effectiveness can decline notably under specialized domain shifts, such as unique imaging conditions or environmental variations. In this work, we introduce Deepbench, a framework designed to assess domain-specific robustness of vision-language models (VLMs). Deepbench leverages a large language model (LLM) to generate realistic, context-aware image corruptions tailored to specific deployment domains without requiring labeled data. We evaluate a range of contrastive vision-language architectures and architectural variants across six real-world domains and observe substantial variability in robustness, highlighting the need for targeted, domain-aware evaluation. Deepbench is released as open-source software to support further research into domain-aware robustness assessment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
