Towards Geographic Inclusion in the Evaluation of Text-to-Image Models

arXiv:2405.04457v1 Announce Type: new
Abstract: Rapid progress in text-to-image generative models coupled with their deployment for visual content creation has magnified the importance of thoroughly evaluating their performance and identifying potential biases. In pursuit of models that generate images that are realistic, diverse, visually appealing, and consistent with the given prompt, researchers and practitioners often turn to automated metrics to facilitate scalable and cost-effective performance profiling. However, commonly-used metrics often fail to account for the full diversity of human preference; …

abstract arxiv biases consistent cs.cv cs.cy cs.hc deployment diverse evaluation generate generative generative models image images importance inclusion performance progress prompt text text-to-image type visual