ImageInWords: Unlocking Hyper-Detailed Image Descriptions

View a PDF of the paper titled ImageInWords: Unlocking Hyper-Detailed Image Descriptions, by Roopal Garg and Andrea Burns and Burcu Karagol Ayan and Yonatan Bitton and Ceslee Montgomery and Yasumasa Onoe and Andrew Bunner and Ranjay Krishna and Jason Baldridge and Radu Soricut

View PDF
HTML (experimental)

Abstract:Despite the longstanding adage “an image is worth a thousand words,” generating accurate hyper-detailed image descriptions remains unsolved. Trained on short web-scraped image text, vision-language models often generate incomplete descriptions with visual inconsistencies. We address this via a novel data-centric approach with ImageInWords (IIW), a carefully designed human-in-the-loop framework for curating hyper-detailed image descriptions. Human evaluations on IIW data show major gains compared to recent datasets (+66%) and GPT4V (+48%) across comprehensiveness, specificity, hallucinations, and more. We also show that fine-tuning with IIW data improves these metrics by +31% against models trained with prior work, even with only 9k samples. Lastly, we evaluate IIW models with text-to-image generation and vision-language reasoning tasks. Our generated descriptions result in the highest fidelity images, and boost compositional reasoning by up to 6% on ARO, SVO-Probes, and Winoground datasets. We release the IIW Eval benchmark with human judgement labels, object and image-level annotations from our framework, and existing image caption datasets enriched via IIW-model.