Synthetic Data from Diffusion Models Improves ImageNet Classification
arXiv:2304.08466
Abstract
Deep generative models are becoming increasingly powerful, now generating diverse high fidelity photo-realistic samples given text prompts. Have they reached the point where models of natural images can be used for generative data augmentation, helping to improve challenging discriminative tasks? We show that large-scale text-to image diffusion models can be fine-tuned to produce class conditional models with SOTA FID (1.76 at 256x256 resolution) and Inception Score (239 at 256x256). The model also yields a new SOTA in Classification Accuracy Scores (64.96 for 256x256 generative samples, improving to 69.24 for 1024x1024 samples). Augmenting the ImageNet training set with samples from the resulting models yields significant improvements in ImageNet classification accuracy over strong ResNet and Vision Transformer baselines.
Cited by in corpus (7)
- Quality-Diversity Generative Sampling for Learning with Synthetic Data
- Multi-Resolution Diffusion for Privacy-Sensitive Recommender Systems
- CIA: Controllable Image Augmentation Framework Based on Stable Diffusion
- Precision at Scale: Domain-Specific Datasets On-Demand
- Image Captions are Natural Prompts for Text-to-Image Models
- Time Series Similarity Score Functions to Monitor and Interact with the Training and Denoising Process of a Time Series Diffusion Model applied to a Human Activity Recognition Dataset based on IMUs
- Semantic Generative Augmentations for Few-Shot Counting