Towards Image Understanding from Deep Compression without Decoding

03/16/2018
by   Robert Torfason, et al.
0

Motivated by recent work on deep neural network (DNN)-based image compression methods showing potential improvements in image quality, savings in storage, and bandwidth reduction, we propose to perform image understanding tasks such as classification and segmentation directly on the compressed representations produced by these compression methods. Since the encoders and decoders in DNN-based compression methods are neural networks with feature-maps as internal representations of the images, we directly integrate these with architectures for image understanding. This bypasses decoding of the compressed representation into RGB space and reduces computational cost. Our study shows that accuracies comparable to networks that operate on compressed RGB images can be achieved while reducing the computational complexity up to 2×. Furthermore, we show that synergies are obtained by jointly training compression networks with classification networks on the compressed representations, improving image quality, classification accuracy, and segmentation performance. We find that inference from compressed representations is particularly advantageous compared to inference from compressed RGB images for aggressive compression rates.

READ FULL TEXT

page 1

page 8

page 14

page 16

research
01/03/2022

Compression-Resistant Backdoor Attack against Deep Neural Networks

In recent years, many backdoor attacks based on training data poisoning ...
research
10/26/2022

SINCO: A Novel structural regularizer for image compression using implicit neural representations

Implicit neural representations (INR) have been recently proposed as dee...
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
01/29/2018

DeepSIC: Deep Semantic Image Compression

Incorporating semantic information into the codecs during image compress...
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
02/19/2023

Deep Selector-JPEG: Adaptive JPEG Image Compression for Computer Vision in Image classification with Human Vision Criteria

With limited storage/bandwidth resources, input images to Computer Visio...
research
06/16/2020

Explorable Decoding of Compressed Images

The ever-growing amounts of visual contents captured on a daily basis ne...

Please sign up or login with your details

Forgot password? Click here to reset