PromptMix: Text-to-image diffusion models enhance the performance of lightweight networks

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review


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%.
Original languageEnglish
Title of host publication2023 International Joint Conference on Neural Networks (IJCNN)
Publication date2023
ISBN (Electronic)978-1-6654-8867-9, 978-1-6654-8868-6
Publication statusPublished - 2023
SeriesIEEE International Joint Conference on Neural Network proceedings


  • Efficient deep learning
  • crowd counting
  • data augmentation
  • lightweight deep learning
  • monocular depth estimation
  • text-to-image diffusion model


Dive into the research topics of 'PromptMix: Text-to-image diffusion models enhance the performance of lightweight networks'. Together they form a unique fingerprint.

Cite this