Year: 2019
Type: preprint
Abstract: Model compression is eminently suited for deploying deep learning on IoT-devices. However, existing model compression techniques rely on access to the original or some alternate dataset. In this paper, we address the model compression problem when no real data is available, e.g., when data is private. To this end, we propose Dream Distillation, a data-independent model compression framework. Our experiments show that Dream Distillation can achieve 88.5% accuracy on the CIFAR-10 test set without actually training on the original data!
Source: arXiv (Cornell University)
Institution: Carnegie Mellon University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2946830201