通过深度生成先验的数据集蒸馏泛化

May, 2023

通过深度生成先验的数据集蒸馏泛化

Generalizing Dataset Distillation via Deep Generative Prior

George Cazenavette, Tongzhou Wang, Antonio Torralba, Alexei A. Efros, Jun-Yan Zhu

TL;DRDataset Distillation technique using learned prior of deep generative models and a new optimization algorithm improves cross-architecture generalization by synthesizing few synthetic images from a large dataset.

Abstract

dataset distillation aims to distill an entire dataset's knowledge into a few synthetic images. The idea is to synthesize a small number of synthetic data points that, when given to a learning algorithm as traini