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

Keywords: Vision-and-language, Image-text alignment, Text-to-image generation, Image-to-text generation, Multi-modal models, Synthetic images, Meta-evaluation, Visual-question-answering

TL;DR: Introducing SeeTRUE, an image-text alignment benchmark; we showcase two methods using question generation, visual QA, and classification, excelling in alignment tasks and enabling text-to-image reordering.

Abstract: 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.

Submission Number: 4455