Saliency-Driven Hierarchical Learned Image Coding for Machines

Fischer K, Brand F, Blum C, Kaup A (2023)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2023

Journal

2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Publisher: Institute of Electrical and Electronics Engineers Inc.

Conference Proceedings Title: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Event location: Rhodes Island

ISBN: 978-1-7281-6328-4

DOI: 10.1109/ICASSP49357.2023.10096674

Abstract

We propose to employ a saliency-driven hierarchical neural image compression network for a machine-to-machine communication scenario following the compress-then-analyze paradigm. By that, different areas of the image are coded at different qualities depending on whether salient objects are located in the corresponding area. Areas without saliency are transmitted in latent spaces of lower spatial resolution in order to reduce the bitrate. The saliency information is explicitly derived from the detections of an object detection network. Furthermore, we propose to add saliency information to the training process in order to further specialize the different latent spaces. All in all, our hierarchical model with all proposed optimizations achieves 77.1 % bitrate savings over the latest video coding standard VVC on the Cityscapes dataset and with Mask R-CNN as analysis network at the decoder side. Thereby, it also outperforms traditional, non-hierarchical compression networks.

Authors with CRIS profile

Kristian Fischer Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS) Fabian Brand Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS) Andre Kaup Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS)

How to cite

APA:

Fischer, K., Brand, F., Blum, C., & Kaup, A. (2023). Saliency-Driven Hierarchical Learned Image Coding for Machines. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Rhodes Island, GR: Institute of Electrical and Electronics Engineers Inc..

MLA:

Fischer, Kristian, et al. "Saliency-Driven Hierarchical Learned Image Coding for Machines." Proceedings of the 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023, Rhodes Island Institute of Electrical and Electronics Engineers Inc., 2023.

BibTeX: Download