Wei Huang, Zhiliang Peng, Li Dong, Furu Wei, Jianbin Jiao...
TL;DR该研究提出了一种通用到特定蒸馏法 (G2SD),以在受掩膜自编码器预训练的大型模型的监督下激发小型 ViT 模型的潜力,从而在图像分类、目标检测和语义分割任务上设置了坚实的基线。
Abstract
Large vision transformers (ViTs) driven by self-supervised pre-training
mechanisms achieved unprecedented progress. Lightweight ViT models limited by
the model capacity, however, benefit little from those pre-tra
Dataset 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.