Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis

by   Zi Wang, et al.

Knowledge distillation (KD) has proved to be an effective approach for deep neural network compression, which learns a compact network (student) by transferring the knowledge from a pre-trained, over-parameterized network (teacher). In traditional KD, the transferred knowledge is usually obtained by feeding training samples to the teacher network to obtain the class probabilities. However, the original training dataset is not always available due to storage costs or privacy issues. In this study, we propose a novel data-free KD approach by modeling the intermediate feature space of the teacher with a multivariate normal distribution and leveraging the soft targeted labels generated by the distribution to synthesize pseudo samples as the transfer set. Several student networks trained with these synthesized transfer sets present competitive performance compared to the networks trained with the original training set and other data-free KD approaches.


page 1

page 2

page 3

page 4


Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model

Knowledge distillation (KD) is a successful approach for deep neural net...

Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion

We introduce DeepInversion, a new method for synthesizing images from th...

Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation

Knowledge Distillation is an effective method to transfer the learning a...

Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay

Data-Free Knowledge Distillation (KD) allows knowledge transfer from a t...

Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation

Knowledge distillation refers to a technique of transferring the knowled...

Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Data

Social media plays a significant role in sharing essential information, ...

DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier

In this era of digital information explosion, an abundance of data from ...