Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tu, Rong-Cheng, Ma, Zi-Ao, Lan, Tian, Zhao, Yuehao, Huang, Heyan, Mao, Xian-Ling
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915031502815232
author Tu, Rong-Cheng
Ma, Zi-Ao
Lan, Tian
Zhao, Yuehao
Huang, Heyan
Mao, Xian-Ling
author_facet Tu, Rong-Cheng
Ma, Zi-Ao
Lan, Tian
Zhao, Yuehao
Huang, Heyan
Mao, Xian-Ling
contents Driven by the remarkable progress in diffusion models, text-to-image generation has made significant strides, creating a pressing demand for automatic quality evaluation of generated images. Current state-of-the-art automatic evaluation methods heavily rely on Multi-modal Large Language Models (MLLMs), particularly powerful commercial models like GPT-4o. While these models are highly effective, their substantial costs limit scalability in large-scale evaluations. Adopting open-source MLLMs is an alternative; however, their performance falls short due to significant limitations in processing multi-modal data compared to commercial MLLMs. To tackle these problems, we first propose a task decomposition evaluation framework based on GPT-4o to automatically construct a new training dataset, where the complex evaluation task is decoupled into simpler sub-tasks, effectively reducing the learning complexity. Based on this dataset, we design innovative training strategies to effectively distill GPT-4o's evaluation capabilities into a 7B open-source MLLM, MiniCPM-V-2.6. Furthermore, to reliably and comprehensively assess prior works and our proposed model, we manually annotate a meta-evaluation benchmark that includes chain-of-thought explanations alongside quality scores for generated images. Experimental results demonstrate that our distilled open-source MLLM significantly outperforms the current state-of-the-art GPT-4o-base baseline, VIEScore, with over 4.6\% improvement in Spearman and Kendall correlations with human judgments.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15488
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark
Tu, Rong-Cheng
Ma, Zi-Ao
Lan, Tian
Zhao, Yuehao
Huang, Heyan
Mao, Xian-Ling
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Driven by the remarkable progress in diffusion models, text-to-image generation has made significant strides, creating a pressing demand for automatic quality evaluation of generated images. Current state-of-the-art automatic evaluation methods heavily rely on Multi-modal Large Language Models (MLLMs), particularly powerful commercial models like GPT-4o. While these models are highly effective, their substantial costs limit scalability in large-scale evaluations. Adopting open-source MLLMs is an alternative; however, their performance falls short due to significant limitations in processing multi-modal data compared to commercial MLLMs. To tackle these problems, we first propose a task decomposition evaluation framework based on GPT-4o to automatically construct a new training dataset, where the complex evaluation task is decoupled into simpler sub-tasks, effectively reducing the learning complexity. Based on this dataset, we design innovative training strategies to effectively distill GPT-4o's evaluation capabilities into a 7B open-source MLLM, MiniCPM-V-2.6. Furthermore, to reliably and comprehensively assess prior works and our proposed model, we manually annotate a meta-evaluation benchmark that includes chain-of-thought explanations alongside quality scores for generated images. Experimental results demonstrate that our distilled open-source MLLM significantly outperforms the current state-of-the-art GPT-4o-base baseline, VIEScore, with over 4.6\% improvement in Spearman and Kendall correlations with human judgments.
title Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.15488