Discernible Compressed Images via Deep Perception Consistency

02/17/2020
by   Zhaohui Yang, et al.
12

Image compression, as one of the fundamental low-level image processing tasks, is very essential for computer vision. Conventional image compression methods tend to obtain compressed images by minimizing their appearance discrepancy with the corresponding original images, but pay little attention to their efficacy in downstream perception tasks, e.g., image recognition and object detection. In contrast, this paper aims to produce compressed images by pursuing both appearance and perception consistency. Based on the encoder-decoder framework, we propose using a pre-trained CNN to extract features of original and compressed images. In addition, the maximum mean discrepancy (MMD) is employed to minimize the difference between feature distributions. The resulting compression network can generate images with high image quality and preserve the consistent perception in the feature domain, so that these images can be well recognized by pre-trained machine learning models. Experiments on benchmarks demonstrate the superiority of the proposed algorithm over comparison methods.

READ FULL TEXT

page 2

page 3

page 5

page 6

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
01/03/2022

Compression-Resistant Backdoor Attack against Deep Neural Networks

In recent years, many backdoor attacks based on training data poisoning ...
research
05/24/2020

JPAD-SE: High-Level Semantics for Joint Perception-Accuracy-Distortion Enhancement in Image Compression

While humans can effortlessly transform complex visual scenes into simpl...
research
07/07/2021

Pragmatic Image Compression for Human-in-the-Loop Decision-Making

Standard lossy image compression algorithms aim to preserve an image's a...
research
04/14/2023

Machine Perception-Driven Image Compression: A Layered Generative Approach

In this age of information, images are a critical medium for storing and...
research
05/04/2023

Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts

Image coding for machines (ICM) aims to compress images to support downs...
research
10/21/2019

Transferable Recognition-Aware Image Processing

Recent progress in image recognition has stimulated the deployment of vi...

Please sign up or login with your details

Forgot password? Click here to reset