Apr, 2024
AesExpert:面向图像美学感知的多模态基础模型
AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception
Yipo Huang, Xiangfei Sheng, Zhichao Yang, Quan Yuan, Zhichao Duan...
TL;DR通过构建 Aesthetic Multi-Modality Instruction Tuning(AesMMIT)数据集,并基于该数据集进行 fine-tuning,实现了 multi-modality Aesthetic Expert 模型,即 AesExpert,其在审美知觉性能方面显著优于当前最先进的 MLLMs