We introduce ImageSet2Text, a novel approach that leverages vision-language foundation models to automatically create natural language descriptions of image sets. Inspired by concept bottleneck models (CBMs) and based on visual-question answering (VQA) chains, ImageSet2Text iteratively extracts key concepts from image subsets, encodes them into a structured graph, and refines insights using an external knowledge graph and CLIP-based validation. This iterative process enhances interpretability and enables accurate and detailed set-level summarization. Through extensive experiments, we evaluate ImageSet2Text's descriptions on accuracy, completeness, readability and overall quality, benchmarking it against existing vision-language models and introducing new datasets for large-scale group image captioning.
View on arXiv@article{riccio2025_2503.19361,
title={ ImageSet2Text: Describing Sets of Images through Text },
author={ Piera Riccio and Francesco Galati and Kajetan Schweighofer and Noa Garcia and Nuria Oliver },
journal={arXiv preprint arXiv:2503.19361},
year={ 2025 }
}