Q-align: teaching LMMs for visual scoring via discrete text-defined levels

• Main Authors: Wu, Haoning, Zhang, Zicheng, Zhang, Weixia, Chen, Chaofeng, Liao, Liang, Li, Chunyi, Gao, Yixuan, Wang, Annan, Zhang, Erli, Sun, Wenxiu, Yan, Qiong, Min, Xiongkuo, Zhai, Guangtao, Lin, Weisi
• Other Authors: College of Computing and Data Science
• Format: Conference or Workshop Item
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Large multi-modality models; Computer vision
• Online Access: https://hdl.handle.net/10356/178466; http://arxiv.org/abs/2312.17090v1; https://openreview.net/forum?id=PHjkVjR78A; https://icml.cc/
• Institution: Nanyang Technological University

The explosion of visual content available online underscores the requirement for an accurate machine assessor to robustly evaluate scores across diverse types of visual contents. While recent studies have demonstrated the exceptional potentials of large multi-modality models (LMMs) on a wide rang...