What You See is What You Read? Improving Text-Image Alignment Evaluation

Michal Yarom · Yonatan Bitton · Soravit Changpinyo · Roee Aharoni · Jonathan Herzig · Oran Lang · Eran Ofek · Idan Szpektor

Great Hall & Hall B1+B2 (level 1) #701
[ ] [ Project Page ]
Wed 13 Dec 3 p.m. PST — 5 p.m. PST


Automatically determining whether a text and a corresponding image are semantically aligned is a significant challenge for vision-language models, with applications in generative text-to-image and image-to-text tasks. In this work, we study methods for automatic text-image alignment evaluation. We first introduce SeeTRUE: a comprehensive evaluation set, spanning multiple datasets from both text-to-image and image-to-text generation tasks, with human judgements for whether a given text-image pair is semantically aligned. We then describe two automatic methods to determine alignment: the first involving a pipeline based on question generation and visual question answering models, and the second employing an end-to-end classification approach by finetuning multimodal pretrained models. Both methods surpass prior approaches in various text-image alignment tasks, with significant improvements in challenging cases that involve complex composition or unnatural images. Finally, we demonstrate how our approaches can localize specific misalignments between an image and a given text, and how they can be used to automatically re-rank candidates in text-to-image generation.

Chat is not available.