Options
ProgDTD: progressive Learned Image compression with double-tail-drop training
Publikationstyp
Conference Paper
Date Issued
2023-06
Sprache
English
Author(s)
Volume
2023
Start Page
1130
End Page
1139
Citation
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition workshops: 1130-1139
Contribution to Conference
Publisher DOI
Scopus ID
Publisher
IEEE
ISBN of container
979-8-3503-0249-3
979-8-3503-0250-9
Progressive compression allows images to start loading as low-resolution versions, becoming clearer as more data is received. This increases user experience when, for example, network connections are slow. Today, most approaches for image compression, both classical and learned ones, are designed to be non-progressive. This paper introduces ProgDTD, a training method that transforms learned, non-progressive image compression approaches into progressive ones. The design of ProgDTD is based on the observation that the information stored within the bottleneck of a compression model commonly varies in importance. To create a progressive compression model, ProgDTD modifies the training steps to enforce the model to store the data in the bottleneck sorted by priority. We achieve progressive compression by transmitting the data in order of its sorted index. ProgDTD is designed for CNN-based learned image compression models, does not need additional parameters, and has a customizable range of progressiveness. For evaluation, we apply ProgDTD to the hyperprior model, one of the most common structures in learned image compression. Our experimental results show that ProgDTD performs comparably to its non-progressive counterparts and other state-of-the-art progressive models in terms of MS-SSIM and accuracy.
Subjects
MLE@TUHH
DDC Class
600: Technology