Instruct Me More! Random Prompting for Visual In-Context Learning

Abstract

Large-scale models trained on extensive datasets, have emerged as the preferred approach due to their high generalizability across various tasks. In-context learning (ICL), a popular strategy in natural language processing, uses such models for different tasks by providing instructive prompts but without updating model parameters. This idea is now being explored in computer vision, where an input-output image pair (called an in-context pair) is supplied to the model with a query image as a prompt to exemplify the desired output. The efficacy of visual ICL often depends on the quality of the prompts. We thus introduce a method coined Instruct Me More (InMeMo), which augments in-context pairs with a learnable perturbation (prompt), to explore its potential. Our experiments on mainstream tasks reveal that InMeMo surpasses the current state-of-the-art performance. Specifically, compared to the baseline without learnable prompt, InMeMo boosts mIoU scores by 7.35 and 15.13 for foreground segmentation and single object detection tasks, respectively. Our findings suggest that InMeMo offers a versatile and efficient way to enhance the performance of visual ICL with lightweight training. Code is available at https://github.com/Jackieam/InMeMo.

Publication
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
Jiahao Zhang
Jiahao Zhang
PhD Student
Bowen Wang
Bowen Wang
Specially-Appointed Researcher/Fellow
Liangzhi Li
Liangzhi Li
Guest Assistant Professor

His research interests lie in deep learning, computer vision, robotics, and medical images.

Yuta Nakashima
Yuta Nakashima
Professor

Yuta Nakashima is a professor with Institute for Datability Science, Osaka University. His research interests include computer vision, pattern recognition, natural langauge processing, and their applications.

Hajime Nagahara
Hajime Nagahara
Professor

He is working on computer vision and pattern recognition. His main research interests lie in image/video recognition and understanding, as well as applications of natural language processing techniques.