MUSCO: Multi-Stage Compression of neural networks
arXiv:1903.09973
Abstract
The low-rank tensor approximation is very promising for the compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with a smart rank selection and fine-tuning. We demonstrate the efficiency of our method comparing to non-iterative ones. Our approach improves the compression rate while maintaining the accuracy for a variety of tasks.
References in corpus (7)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- Fixed Point Quantization of Deep Convolutional Networks
- Speeding up Convolutional Neural Networks with Low Rank Expansions
- Convolutional Neural Networks using Logarithmic Data Representation
- Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses