Analyzing and Mitigating Compression Defects in Deep Learning

11/17/2020
by   Max Ehrlich, et al.
1

With the proliferation of deep learning methods, many computer vision problems which were considered academic are now viable in the consumer setting. One drawback of consumer applications is lossy compression, which is necessary from an engineering standpoint to efficiently and cheaply store and transmit user images. Despite this, there has been little study of the effect of compression on deep neural networks and benchmark datasets are often losslessly compressed or compressed at high quality. Here we present a unified study of the effects of JPEG compression on a range of common tasks and datasets. We show that there is a significant penalty on common performance metrics for high compression. We test several methods for mitigating this penalty, including a novel method based on artifact correction which requires no labels to train.

READ FULL TEXT

page 6

page 11

page 12

page 13

page 15

page 16

page 17

page 18

research
04/04/2022

The First Principles of Deep Learning and Compression

The deep learning revolution incited by the 2012 Alexnet paper has been ...
research
03/27/2020

Image compression optimized for 3D reconstruction by utilizing deep neural networks

Computer vision tasks are often expected to be executed on compressed im...
research
05/19/2023

Deep Image Compression Using Scene Text Quality Assessment

Image compression is a fundamental technology for Internet communication...
research
05/11/2023

A Deep Learning-based Compression and Classification Technique for Whole Slide Histopathology Images

This paper presents an autoencoder-based neural network architecture to ...
research
09/25/2019

Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network

One of biggest issues in deep learning theory is its generalization abil...
research
09/02/2020

Depth Range Reduction for 3D Range Geometry Compression

Three-dimensional (3D) shape measurement devices and techniques are bein...
research
09/12/2019

Debreach: Mitigating Compression Side Channels via Static Analysis and Transformation

Compression is an emerging source of exploitable side-channel leakage th...

Please sign up or login with your details

Forgot password? Click here to reset