Training on Thin Air: Improve Image Classification with Generated Data
This addresses data scarcity for image classification tasks, offering a practical solution with significant performance gains, though it builds on existing generative models.
The paper tackles the challenge of acquiring high-quality training data for image classification by introducing Diffusion Inversion, a method that uses Stable Diffusion to generate diverse training images, resulting in a 2-3x improvement in sample complexity and a 6.5x reduction in sampling time.
Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the pre-trained generative model, Stable Diffusion, to generate diverse, high-quality training data for image classification. Our approach captures the original data distribution and ensures data coverage by inverting images to the latent space of Stable Diffusion, and generates diverse novel training images by conditioning the generative model on noisy versions of these vectors. We identify three key components that allow our generated images to successfully supplant the original dataset, leading to a 2-3x enhancement in sample complexity and a 6.5x decrease in sampling time. Moreover, our approach consistently outperforms generic prompt-based steering methods and KNN retrieval baseline across a wide range of datasets. Additionally, we demonstrate the compatibility of our approach with widely-used data augmentation techniques, as well as the reliability of the generated data in supporting various neural architectures and enhancing few-shot learning.