基于视觉和语言模型的合成数据生成基础
Grounding Synthetic Data Generation With Vision and Language Models
AI总结：
本文提出一种视觉-语言 grounded 框架，用于可解释的遥感合成数据增强与评估，引入 ARAS400k 数据集，包含 100k 真实图像和 300k 合成图像，用于语义分割和图像描述生成。
摘要：
深度学习模型受益于数据多样性和体积的增加，推动了合成数据增强以改进现有数据集。然而，现有合成数据评估指标通常计算潜在特征相似性，难以解释且不总是与下游任务的贡献相关。我们提出了一种视觉-语言 grounded 框架，用于可解释的合成数据增强和评估。我们的方法结合生成模型、语义分割和图像描述生成与视觉和语言模型。基于此框架，我们引入了 ARAS400k：一个大规模遥感数据集，通过合成数据增强用于分割和描述生成，包含 100k 真实图像和 300k 合成图像，每张图像均配以分割图和描述。ARAS400k 通过分析语义组成、减少描述冗余并验证视觉结构与语言描述之间的跨模态一致性，实现了合成数据的自动化评估。实验结果表明，仅训练于合成数据的模型达到竞争性性能水平，而训练于增强数据（真实和合成图像的组合）的模型在一致性和性能上均优于真实数据基线。因此，本文建立了遥感任务的可扩展基准，特别是在语义分割和图像描述生成方面。该数据集可在 zenodo.org/records/18890661 获取，代码库在 github.com/caglarmert/ARAS400k。
英文摘要：
Deep learning models benefit from increasing data diversity and volume, motivating synthetic data augmentation to improve existing datasets. However, existing evaluation metrics for synthetic data typically calculate latent feature similarity, which is difficult to interpret and does not always correlate with the contribution to downstream tasks. We propose a vision-language grounded framework for interpretable synthetic data augmentation and evaluation in remote sensing. Our approach combines generative models, semantic segmentation and image captioning with vision and language models. Based on this framework, we introduce ARAS400k: A large-scale Remote sensing dataset Augmented with Synthetic data for segmentation and captioning, containing 100k real images and 300k synthetic images, each paired with segmentation maps and descriptions. ARAS400k enables the automated evaluation of synthetic data by analyzing semantic composition, minimizing caption redundancy, and verifying cross-modal consistency between visual structures and language descriptions. Experimental results indicate that while models trained exclusively on synthetic data reach competitive performance levels, those trained with augmented data (a combination of real and synthetic images) consistently outperform real-data baselines. Consequently, this work establishes a scalable benchmark for remote sensing tasks, specifically in semantic segmentation and image captioning. The dataset is available at zenodo.org/records/18890661 and the code base at github.com/caglarmert/ARAS400k.
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。
