Toward verifiable and reproducible human evaluation for text-to-image generation

概要

Human evaluation is critical for validating the performance of text-to-image generative models, as this highly cognitive process requires deep comprehension of text and images. However, our survey of 37 recent papers reveals that many works rely solely on automatic measures (eg, FID) or perform poorly described human evaluations that are not reliable or repeatable. This paper proposes a standardized and well-defined human evaluation protocol to facilitate verifiable and reproducible human evaluation in future works. In our pilot data collection, we experimentally show that the current automatic measures are incompatible with human perception in evaluating the performance of the text-to-image generation results. Furthermore, we provide insights for designing human evaluation experiments reliably and conclusively. Finally, we make several resources publicly available to the community to facilitate easy and fast implementations.

論文種別
発表文献
Proc.~IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
中島悠太
中島悠太
准教授

コンピュータビジョン・パターン認識などの研究。ディープニューラルネットワークなどを用いた画像・映像の認識・理解を主に、自然言語処理を援用した応用研究などに従事。