Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Pengfei, Peng, Xiaopeng, Song, Jiajun, Li, Chuanhao, Xu, Zhaopan, Yang, Yue, Guo, Ziyao, Zhang, Hao, Lin, Yuqi, He, Yefei, Zhao, Lirui, Liu, Shuo, Li, Tianhua, Xie, Yuxuan, Chang, Xiaojun, Qiao, Yu, Shao, Wenqi, Zhang, Kaipeng
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.18499
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915218241617920
author Zhou, Pengfei
Peng, Xiaopeng
Song, Jiajun
Li, Chuanhao
Xu, Zhaopan
Yang, Yue
Guo, Ziyao
Zhang, Hao
Lin, Yuqi
He, Yefei
Zhao, Lirui
Liu, Shuo
Li, Tianhua
Xie, Yuxuan
Chang, Xiaojun
Qiao, Yu
Shao, Wenqi
Zhang, Kaipeng
author_facet Zhou, Pengfei
Peng, Xiaopeng
Song, Jiajun
Li, Chuanhao
Xu, Zhaopan
Yang, Yue
Guo, Ziyao
Zhang, Hao
Lin, Yuqi
He, Yefei
Zhao, Lirui
Liu, Shuo
Li, Tianhua
Xie, Yuxuan
Chang, Xiaojun
Qiao, Yu
Shao, Wenqi
Zhang, Kaipeng
contents Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding and generation tasks. However, generating interleaved image-text content remains a challenge, which requires integrated multimodal understanding and generation abilities. While the progress in unified models offers new solutions, existing benchmarks are insufficient for evaluating these methods due to limitations in data size and diversity. To bridge this gap, we introduce OpenING, a comprehensive benchmark comprising 5,400 high-quality human-annotated instances across 56 real-world tasks. OpenING covers diverse daily scenarios such as travel guide, design, and brainstorming, offering a robust platform for challenging interleaved generation methods. In addition, we present IntJudge, a judge model for evaluating open-ended multimodal generation methods. Trained with a novel data pipeline, our IntJudge achieves an agreement rate of 82.42% with human judgments, outperforming GPT-based evaluators by 11.34%. Extensive experiments on OpenING reveal that current interleaved generation methods still have substantial room for improvement. Key findings on interleaved image-text generation are further presented to guide the development of next-generation models.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18499
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation
Zhou, Pengfei
Peng, Xiaopeng
Song, Jiajun
Li, Chuanhao
Xu, Zhaopan
Yang, Yue
Guo, Ziyao
Zhang, Hao
Lin, Yuqi
He, Yefei
Zhao, Lirui
Liu, Shuo
Li, Tianhua
Xie, Yuxuan
Chang, Xiaojun
Qiao, Yu
Shao, Wenqi
Zhang, Kaipeng
Computer Vision and Pattern Recognition
Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding and generation tasks. However, generating interleaved image-text content remains a challenge, which requires integrated multimodal understanding and generation abilities. While the progress in unified models offers new solutions, existing benchmarks are insufficient for evaluating these methods due to limitations in data size and diversity. To bridge this gap, we introduce OpenING, a comprehensive benchmark comprising 5,400 high-quality human-annotated instances across 56 real-world tasks. OpenING covers diverse daily scenarios such as travel guide, design, and brainstorming, offering a robust platform for challenging interleaved generation methods. In addition, we present IntJudge, a judge model for evaluating open-ended multimodal generation methods. Trained with a novel data pipeline, our IntJudge achieves an agreement rate of 82.42% with human judgments, outperforming GPT-based evaluators by 11.34%. Extensive experiments on OpenING reveal that current interleaved generation methods still have substantial room for improvement. Key findings on interleaved image-text generation are further presented to guide the development of next-generation models.
title OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.18499