CIA: Controllable Image Augmentation Framework Based on Stable Diffusion
(2024) 2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR) — Location: San Jose, CA, USA (7.August.2024)
Files
CIA_Controllable_Image_Augmentation_Framework_Based_on_Stable_Diffusion.pdf
Open Access - Adobe PDF
- 8.16 MB
Details
- Authors
- et. al.
- Abstract
- 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.
- Affiliations
Citations
Mohamed Benkedadra; Dany Rimez; Tiffanie Godelaine, & et al. (2024). CIA: Controllable Image Augmentation Framework Based on Stable Diffusion. 2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), Proceedings. Published. 2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), San Jose, CA, USA. https://doi.org/10.1109/MIPR62202.2024.00102 (Original work published 2024)