Wavelet Feature Maps Compression for Image-to-Image CNNs

05/24/2022
by   Shahaf E. Finder, et al.
0

Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less than 4-bits) performs well for classification, it may cause severe performance degradation in image-to-image tasks such as semantic segmentation and depth estimation. In this paper, we propose Wavelet Compressed Convolution (WCC) – a novel approach for high-resolution activation maps compression integrated with point-wise convolutions, which are the main computational cost of modern architectures. To this end, we use an efficient and hardware-friendly Haar-wavelet transform, known for its effectiveness in image compression, and define the convolution on the compressed activation map. We experiment on various tasks, that benefit from high-resolution input, and by combining WCC with light quantization, we achieve compression rates equivalent to 1-4bit activation quantization with relatively small and much more graceful degradation in performance.

READ FULL TEXT

page 5

page 7

page 9

page 17

research
10/10/2021

Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks

Graph Convolutional Networks (GCNs) are widely used in a variety of appl...
research
08/06/2018

Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform

Dense pixelwise prediction such as semantic segmentation is an up-to-dat...
research
01/29/2018

DeepSIC: Deep Semantic Image Compression

Incorporating semantic information into the codecs during image compress...
research
12/10/2018

Accelerating Convolutional Neural Networks via Activation Map Compression

The deep learning revolution brought us an extensive array of neural net...
research
03/30/2016

Vector Quantization for Machine Vision

This paper shows how to reduce the computational cost for a variety of c...
research
10/29/2020

Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks

Compressing large neural networks is an important step for their deploym...
research
07/28/2020

On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures

Recent advances in generalized image understanding have seen a surge in ...

Please sign up or login with your details

Forgot password? Click here to reset