MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning

• Main Authors: Zhao, Haozhe, Cai, Zefan, Si, Shuzheng, Ma, Xiaojian, An, Kaikai, Chen, Liang, Liu, Zixuan, Wang, Sheng, Han, Wenjuan, Chang, Baobao
• Format: Journal Article
• Language: English
• Published: 14.09.2023
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Computation and Language; Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2309.07915

Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with in-context learning, most VLMs still struggle with understanding complex multi-modal prompts with multiple images, making VLMs less effective in downstream vision-language tasks. In this paper, we address the limitation above by 1) introducing vision-language Model with Multi-Modal In-Context Learning(MMICL), a new approach to allow the VLM to deal with multi-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts. Our experiments confirm that MMICL achieves new state-of-the-art zero-shot performance on a wide range of general vision-language tasks, especially for complex benchmarks, including MME and MMBench. Our analysis demonstrates that MMICL effectively tackles the challenge of complex multi-modal prompt understanding and emerges the impressive ICL ability. Furthermore, we observe that MMICL successfully alleviates language bias in VLMs, a common issue for VLMs that often leads to hallucination when faced with extensive textual context. Our code, dataset, dataset tool, and model are available at https://github.com/PKUnlp-icler/MIC