Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer

by   Chen Zhu, et al.

When large scale training data is available, one can obtain compact and accurate networks to be deployed in resource-constrained environments effectively through quantization and pruning. However, training data are often protected due to privacy concerns and it is challenging to obtain compact networks without data. We study data-free quantization and pruning by transferring knowledge from trained large networks to compact networks. Auxiliary generators are simultaneously and adversarially trained with the targeted compact networks to generate synthetic inputs that maximize the discrepancy between the given large network and its quantized or pruned version. We show theoretically that the alternating optimization for the underlying minimax problem converges under mild conditions for pruning and quantization. Our data-free compact networks achieve competitive accuracy to networks trained and fine-tuned with training data. Our quantized and pruned networks achieve good performance while being more compact and lightweight. Further, we demonstrate that the compact structure and corresponding initialization from the Lottery Ticket Hypothesis can also help in data-free training.



page 11


QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization

Deep learning-based face recognition models follow the common trend in d...

Diversifying Sample Generation for Accurate Data-Free Quantization

Quantization has emerged as one of the most prevalent approaches to comp...

CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps

This paper proposes a training method having multiple cyclic training fo...

Paoding: Supervised Robustness-preserving Data-free Neural Network Pruning

When deploying pre-trained neural network models in real-world applicati...

Joint Pruning Quantization for Extremely Sparse Neural Networks

We investigate pruning and quantization for deep neural networks. Our go...

APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

We present APQ for efficient deep learning inference on resource-constra...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.