Dreaming to distill: Data-free knowledge transfer via deepinversion

Hongxu Yin, Pavlo Molchanov, Jose M. Alvarez, Zhizhong Li, Arun Mallya, Derek Hoiem, Niraj K. Jha, Jan Kautz

Research output: Contribution to journalConference articlepeer-review

339 Scopus citations

Abstract

We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network. We "invert"a trained network (teacher) to synthesize class-conditional input images starting from random noise, without using any additional information about the training dataset. Keeping the teacher fixed, our method optimizes the input while regularizing the distribution of intermediate feature maps using information stored in the batch normalization layers of the teacher. Further, we improve the diversity of synthesized images using Adaptive DeepInversion, which maximizes the Jensen-Shannon divergence between the teacher and student network logits. The resulting synthesized images from networks trained on the CIFAR-10 and ImageNet datasets demonstrate high fidelity and degree of realism, and help enable a new breed of data-free applications - ones that do not require any real images or labeled data. We demonstrate the applicability of our proposed method to three tasks of immense practical importance - (i) data-free network pruning, (ii) data-free knowledge transfer, and (iii) data-free continual learning.

Original languageEnglish (US)
Article number9156864
Pages (from-to)8712-8721
Number of pages10
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
StatePublished - 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: Jun 14 2020Jun 19 2020

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Dreaming to distill: Data-free knowledge transfer via deepinversion'. Together they form a unique fingerprint.

Cite this