Video tracking

Algorithm

Deep neural networks

Quantization (signal processing)

Biology

Uncompressed video

Pruning

Contextual image classification

Computation

Computer science

Pattern recognition (psychology)

Image (mathematics)

Object (grammar)

Agronomy

Artificial intelligence

Deep learning

Artificial neural network

Residual neural network

Machine learning

Deep neural networks enable state-of-the-art accuracy on visual recognition tasks such as image classification and object detection. However, modern deep networks contain millions of learned weights; a more efficient utilization of computation resources would assist in a variety of deployment scenarios, from embedded platforms with resource constraints to computing clusters running ensembles of networks. In this paper, we combine network pruning and weight quantization in a single learning framework that performs pruning and quantization jointly, and in parallel with fine-tuning. This allows us to take advantage of the complementary nature of pruning and quantization and to recover from premature pruning errors, which is not possible with current two-stage approaches. Our proposed CLIP-Q method (Compression Learning by In-Parallel Pruning-Quantization) compresses AlexNet by 51-fold, GoogLeNet by 10-fold, and ResNet-50 by 15-fold, while preserving the uncompressed network accuracies on ImageNet.

CLIP-Q: Deep Network Compression Learning by In-parallel Pruning-Quantization