ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Training
Paper i proceeding, 2023

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.

Författare

Ali Hojjat

Christian-Albrechts-Universität zu Kiel

Janek Haberer

Christian-Albrechts-Universität zu Kiel

Olaf Landsiedel

Nätverk och System

Christian-Albrechts-Universität zu Kiel

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

21607508 (ISSN) 21607516 (eISSN)

Vol. 2023-June 1130-1139
9798350302493 (ISBN)

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Vancouver, Canada,

Ämneskategorier

Datavetenskap (datalogi)

DOI

10.1109/CVPRW59228.2023.00120

Mer information

Senast uppdaterat

2023-09-25