Effective Data Augmentation With Diffusion Models
arXiv:2302.07944
Abstract
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.
Update to ICLR 2024 manuscript (https://openreview.net/forum?id=ZWzUA9zeAg), add leafy spurge citations
Cited by in corpus (6)
- Synthetic Data Generation Using Large Language Models: Advances in Text and Code
- Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage
- Multi-Resolution Diffusion for Privacy-Sensitive Recommender Systems
- CIA: Controllable Image Augmentation Framework Based on Stable Diffusion
- Image Captions are Natural Prompts for Text-to-Image Models
- Semantic Generative Augmentations for Few-Shot Counting