Fast Lossless Neural Compression with Integer-Only Discrete Flows

By Siyu Wang, Jianfei Chen, Chongxuan Li, Jun Zhu. 2022

8 citations recorded by the source corpus.

By applying entropy codecs with learned data distributions, neural compressors have significantly outperformed traditional codecs in terms of compression ratio. However, the high inference latency of neural networks hinders the deployment of neural compressors in practical applications. In this work, we propose Integer-only Discrete Flows (IODF), an efficient neural compressor with integer-only arithmetic. Our work is built upon integer discrete flows, which consists of invertible transformations between discrete random variables. We propose efficient invertible transformations with integer-only arithmetic based on 8-bit quantization. Our invertible transformation is equipped with learnable binary gates to remove redundant filters during inference. We deploy IODF with TensorRT on GPUs, achieving 10x inference speedup compared to the fastest existing neural compressors, while retaining the high compression rates on ImageNet32 and ImageNet64.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hang Su
2. Jun Zhu
3. Liyuan Wang
4. Xingxing Zhang
5. Yang He
6. Lingao Xiao
7. Tianyu Pang
8. Yinpeng Dong

In Computer Vision and Pattern Recognition

1. Hang Su
2. Jun Zhu
3. Liyuan Wang
4. Xingxing Zhang
5. Yang He
6. Lingao Xiao
7. Yinpeng Dong
8. Vamsi Krishna Ithapu

In Generative Models

1. Yang He
2. Lingao Xiao
3. Liyuan Wang
4. Jun Zhu
5. Hang Su
6. Xingxing Zhang

In Efficiency & Compression

1. Lingao Xiao
2. Yang He
3. Liyuan Wang
4. Jun Zhu
5. Hang Su
6. Xingxing Zhang

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “Neural Compression [9], [297], [435] instead expliots generative models to optimize the storage overhead of input data without much distortion, which can benefit both efficacy”
• Structured Pruning for Deep Convolutional Neural Networks: A Survey (2023, methodology): “IODF [164] utilizes integer-only arithmetic based on 8-bit quantization and has learnable binary gates to eliminate redundant filters during inference.”