تقرير
All in an Aggregated Image for In-Image Learning
| العنوان: | All in an Aggregated Image for In-Image Learning |
|---|---|
| المؤلفون: | Wang, Lei, Xu, Wanyu, Hu, Zhiqiang, Lan, Yihuai, Dong, Shan, Wang, Hao, Lee, Roy Ka-Wei, Lim, Ee-Peng |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Computation and Language |
| الوصف: | This paper introduces a new in-context learning (ICL) mechanism called In-Image Learning (I$^2$L) that combines demonstration examples, visual cues, and chain-of-thought reasoning into an aggregated image to enhance the capabilities of Large Multimodal Models (e.g., GPT-4V) in multimodal reasoning tasks. Unlike previous approaches that rely on converting images to text or incorporating visual input into language models, I$^2$L consolidates all information into an aggregated image and leverages image processing, understanding, and reasoning abilities. This has several advantages: it reduces inaccurate textual descriptions of complex images, provides flexibility in positioning demonstration examples, and avoids multiple input images and lengthy prompts. We also introduce I$^2$L-Hybrid, a method that combines the strengths of I$^2$L with other ICL methods. Specifically, it uses an automatic strategy to select the most suitable method (I$^2$L or another certain ICL method) for a specific task instance. We conduct extensive experiments to assess the effectiveness of I$^2$L and I$^2$L-Hybrid on MathVista, which covers a variety of complex multimodal reasoning tasks. Additionally, we investigate the influence of image resolution, the number of demonstration examples in a single image, and the positions of these demonstrations in the aggregated image on the effectiveness of I$^2$L. Our code is publicly available at https://github.com/AGI-Edgerunners/IIL. Comment: Preprint |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2402.17971 |
| رقم الأكسشن: | edsarx.2402.17971 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |