Impact of Synthetic Data on Cross-Modal Retrieval Accuracy in Vision-Language Models

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. Base

Research goal: To what extent does synthetic data generation for class imbalance correction degrade cross-modal retrieval accuracy in vision-language models?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.8/10.