Remote Sensing Image Coding for Machines on Semantic Segmentation via Contrastive Learning

Due to the huge data volume of high-resolution remote sensing imagery (RSI) and limited transmission bandwidth, RSIs are typically compressed for efficient transmission and storage. However, most of the existing compression algorithms are developed based on optimizing for the human perceptual that a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing Vol. 62; pp. 1 - 13
Main Authors: Zhang, Junxi, Chen, Zhenzhong, Liu, Shan
Format: Journal Article
Language:English
Published: New York IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Bit rate
Clustering
Codecs
Compression
Contrastive learning
Decision making
Feature extraction
Image coding
image coding for machines (ICMs)
Image compression
Image processing
Image resolution
Image segmentation
Information processing
Learning
Object recognition
Object segmentation
Pattern recognition
Remote sensing
remote sensing interpretation
Semantic segmentation
Semantics
Transform coding
ISSN:0196-2892, 1558-0644
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Due to the huge data volume of high-resolution remote sensing imagery (RSI) and limited transmission bandwidth, RSIs are typically compressed for efficient transmission and storage. However, most of the existing compression algorithms are developed based on optimizing for the human perceptual that are not suitable for remote sensing image applications where RSIs are usually used for machine interpretation tasks, such as semantic segmentation for ground-object recognition. In this article, we propose an image coding for machines (ICMs) paradigm based on contrastive learning in a fully supervised manner to boost semantic segmentation of compressed RSIs. Specifically, we build an end-to-end compression framework to make full use of the global semantic information by clustering intracategory projected embeddings and spacing intercategory embeddings apart, to compensate for the loss of feature discriminability during the compression process and reconstruct the decision boundaries between different categories. Compared to the state-of-the-art image compression methods, our proposed method significantly improves the performance of semantic segmentation on the remote sensing labeling benchmark datasets.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2024.3479190