Few-Shot Image Classification and Segmentation as Visual Question Answering Using Vision-Language Models
This work addresses the challenge of classifying and segmenting objects with limited examples, which is crucial for applications like robotics and autonomous systems, though it is incremental as it builds on existing vision-language models.
The paper tackles few-shot image classification and segmentation by converting it into a visual question answering problem using vision-language models, achieving state-of-the-art results on Pascal-5i and COCO-20i datasets.
The task of few-shot image classification and segmentation (FS-CS) involves classifying and segmenting target objects in a query image, given only a few examples of the target classes. We introduce the Vision-Instructed Segmentation and Evaluation (VISE) method that transforms the FS-CS problem into the Visual Question Answering (VQA) problem, utilising Vision-Language Models (VLMs), and addresses it in a training-free manner. By enabling a VLM to interact with off-the-shelf vision models as tools, the proposed method is capable of classifying and segmenting target objects using only image-level labels. Specifically, chain-of-thought prompting and in-context learning guide the VLM to answer multiple-choice questions like a human; vision models such as YOLO and Segment Anything Model (SAM) assist the VLM in completing the task. The modular framework of the proposed method makes it easily extendable. Our approach achieves state-of-the-art performance on the Pascal-5i and COCO-20i datasets.