Q-instruct: improving low-level visual abilities for multi-modality foundation models

• Main Authors: Wu, Haoning, Zhang, Zicheng, Zhang, Erli, Chen, Chaofeng, Liao, Liang, Wang, Annan, Xu, Kaixin, Li, Chunyi, Hou, Jingwen, Zhai, Guangtao, Xue, Geng, Sun, Wenxiu, Yan, Qiong, Lin, Weisi
• Other Authors: College of Computing and Data Science
• Format: Conference or Workshop Item
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Multi-modality large language models; Computer vision
• Online Access: https://hdl.handle.net/10356/178464; http://arxiv.org/abs/2311.06783v1; https://openaccess.thecvf.com/content/CVPR2024/papers/Wu_Q-Instruct_Improving_Low-level_Visual_Abilities_for_Multi-modality_Foundation_Models_CVPR_2024_paper.pdf
• Institution: Nanyang Technological University

Multi-modality foundation models, as represented by GPT-4V, have brought a new paradigm for low-level visual perception and understanding tasks, that can respond to a broad range of natural human instructions in a model. While existing foundation models have shown exciting potentials on low-level visual tasks, their related abilities are still preliminary and need to be improved. In order to enhance these models, we conduct a large-scale subjective experiment collecting a vast number of real human feedbacks on low-level vision. Each feedback follows a pathway that starts with a detailed description on the low-level visual appearance (*e.g. clarity, color, brightness* of an image, and ends with an overall conclusion, with an average length of 45 words. The constructed **Q-Pathway** dataset includes 58K detailed human feedbacks on 18,973 images with diverse low-level appearance. Moreover, to enable foundation models to robustly respond to diverse types of questions, we design a GPT-participated conversion to process these feedbacks into diverse-format 200K instruction-response pairs. Experimental results indicate that the **Q-Instruct** consistently elevates low-level perception and understanding abilities across several foundational models. We anticipate that our datasets can pave the way for a future that general intelligence can perceive, understand low-level visual appearance and evaluate visual quality like a human. Our dataset, model zoo, and demo is published at: https://q-future.github.io/Q-Instruct.