CIA: Controllable Image Augmentation Framework Based on Stable Diffusion
This work addresses data scarcity for object detection systems, offering a modular tool for dataset augmentation, though it is incremental as it builds on existing diffusion models.
The authors tackled the problem of limited annotated datasets for computer vision tasks by developing CIA, a controllable image augmentation framework based on Stable Diffusion, which significantly improved human object detection performance, approaching gains from doubling real data.
Computer vision tasks such as object detection and segmentation rely on the availability of extensive, accurately annotated datasets. In this work, We present CIA, a modular pipeline, for (1) generating synthetic images for dataset augmentation using Stable Diffusion, (2) filtering out low quality samples using defined quality metrics, (3) forcing the existence of specific patterns in generated images using accurate prompting and ControlNet. In order to show how CIA can be used to search for an optimal augmentation pipeline of training data, we study human object detection in a data constrained scenario, using YOLOv8n on COCO and Flickr30k datasets. We have recorded significant improvement using CIA-generated images, approaching the performances obtained when doubling the amount of real images in the dataset. Our findings suggest that our modular framework can significantly enhance object detection systems, and make it possible for future research to be done on data-constrained scenarios. The framework is available at: github.com/multitel-ai/CIA.