Conditional Encoder-Based Adaptive Deep Image Compression with Classification-Driven Semantic Awareness

This paper proposes a new algorithm for adaptive deep image compression (DIC) that can compress images for different purposes or contexts at different rates. The algorithm can compress images with semantic awareness, which means classification-related semantic features are better protected in lossy...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Electronics (Basel) Ročník 12; číslo 13; s. 2781
Hlavní autoři: Lei, Zhongyue, Zhang, Weicheng, Hong, Xuemin, Shi, Jianghong, Su, Minxian, Lin, Chaoheng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.07.2023
Témata:
Accuracy
Adaptation
Adaptive algorithms
Algorithms
Classification
Coders
Data compression
Entropy
Image classification
Image coding
Image compression
Image processing
Machine learning
Methods
Neural networks
Optimization
Semantics
China
ISSN:2079-9292, 2079-9292
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper proposes a new algorithm for adaptive deep image compression (DIC) that can compress images for different purposes or contexts at different rates. The algorithm can compress images with semantic awareness, which means classification-related semantic features are better protected in lossy image compression. It builds on the existing conditional encoder-based DIC method and adds two features: a model-based rate-distortion-classification-perception (RDCP) framework to control the trade-off between rate and performance for different contexts, and a mechanism to generate coding conditions based on image complexity and semantic importance. The algorithm outperforms the QMAP2021 benchmark on the ImageNet dataset. Over the tested rate range, it improves the classification accuracy by 11% and the perceptual quality by 12.4%, 32%, and 1.3% on average for NIQE, LPIPS, and FSIM metrics, respectively.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics12132781