Effective Data Augmentation With Diffusion Models
By Brandon Trabucco, Kyle Doherty, Max Gurinas, Ruslan Salakhutdinov. International Conference on Learning Representations, 2023
415 citations recorded by the source corpus.
Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation learning. The standard approach to data augmentation combines simple transformations like rotations and flips to generate new images from existing ones. However, these new images lack diversity along key semantic axes present in the data. Current augmentations cannot alter the high-level semantic attributes, such as animal species present in a scene, to enhance the diversity of data. We address the lack of diversity in data augmentation with image-to-image transformations parameterized by pre-trained text-to-image diffusion models. Our method edits images to change their semantics using an off-the-shelf diffusion model, and generalizes to novel visual concepts from a few labelled examples. We evaluate our approach on few-shot image classification tasks, and on a real-world weed recognition task, and observe an improvement in accuracy in tested domains.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/1e05c5427d6a35a3b1bf37fb955f2ea94995a71d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohammad Norouzi
- David J. Fleet
- Simon Kornblith
- Chitwan Saharia
- Quoc V. Le
- Shekoofeh Azizi
- Geoffrey E. Hinton
- Sergey Levine
Citations in the corpus
- Synthetic Data from Diffusion Models Improves ImageNet Classification (2023, background): “Trabucco et al. [65] explore strategies to augment individual images using a pretrained diffusion model, demonstrating improvements in few-shot settings.”