HCF: Hierarchical Cascade Framework for Distributed Multi-Stage Image Compression
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (17) · 14502-14510
DOI: 10.1609/aaai.v40i17.38467 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Junhao Cai und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Distributed multi-stage image compression—where visual content traverses multiple processing nodes under varying quality requirements—poses challenges. Progressive methods enable bitstream truncation but underutilize available compute resources; successive compression repeats costly pixel-domain operations and suffers cumulative quality loss and inefficiency; fixed-parameter models lack post-encoding flexibility. In this work, we developed the Hierarchical Cascade Framework (HCF) that achieves high rate-distortion performance and better computational efficiency through direct latent-space transformations across network nodes in distributed multi-stage image compression systems. Under HCF, we introduced policy-driven quantization control to optimize rate–distortion trade-offs, and established the edge quantization principle through differential entropy analysis. The configuration based on this principle demonstrates up to 0.6dB PSNR gains over other configurations. When comprehensively evaluated on the Kodak, CLIC, and CLIC2020-mobile datasets, HCF outperforms successive-compression methods by up to 5.56% BD-Rate in PSNR on CLIC, while saving up to 97.8% FLOPs, 96.5% GPU memory, and 90.0% execution time. It also outperforms state-of-the-art progressive compression methods by up to 12.64% BD-Rate on Kodak and enables retraining-free cross-quality adaptation with 7.13-10.87% BD-Rate reductions on CLIC2020-mobile.
Zitieren
APA
Cai, J., An, T., Jin, C., Choi, S. I., Park, J., & Joo, C. (2026). HCF: Hierarchical Cascade Framework for Distributed Multi-Stage Image Compression. Proceedings of the AAAI Conference on Artificial Intelligence, 40(17), 14502-14510. https://doi.org/10.1609/aaai.v40i17.38467
Vancouver
Cai J, An T, Jin C, Choi SI, Park J, Joo C. HCF: Hierarchical Cascade Framework for Distributed Multi-Stage Image Compression. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(17):14502-14510. doi:10.1609/aaai.v40i17.38467
BibTeX
@article{Cai2026,
author = {Cai, Junhao and An, Taegun and Jin, Chengjun and Choi, Sung Il and Park, Juhyun and Joo, Changhee},
title = {HCF: Hierarchical Cascade Framework for Distributed Multi-Stage Image Compression},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {17},
pages = {14502--14510},
doi = {10.1609/aaai.v40i17.38467}
}
EUVIMED