PromptMix: Text-to-image diffusion models enhance the performance of lightweight networks
This addresses the challenge of limited annotations for lightweight networks in computer vision, offering an incremental improvement over existing data augmentation techniques.
The paper tackles the problem of small dataset sizes in dense regression tasks like crowd counting by introducing PromptMix, a method that generates synthetic images using text-to-image diffusion models and annotates them with high-performing networks, boosting lightweight network performance by up to 26% in experiments.
Many deep learning tasks require annotations that are too time consuming for human operators, resulting in small dataset sizes. This is especially true for dense regression problems such as crowd counting which requires the location of every person in the image to be annotated. Techniques such as data augmentation and synthetic data generation based on simulations can help in such cases. In this paper, we introduce PromptMix, a method for artificially boosting the size of existing datasets, that can be used to improve the performance of lightweight networks. First, synthetic images are generated in an end-to-end data-driven manner, where text prompts are extracted from existing datasets via an image captioning deep network, and subsequently introduced to text-to-image diffusion models. The generated images are then annotated using one or more high-performing deep networks, and mixed with the real dataset for training the lightweight network. By extensive experiments on five datasets and two tasks, we show that PromptMix can significantly increase the performance of lightweight networks by up to 26%.