Adaptive Channel Scheduling for Acceleration and Fine Control of RNN-Based Image Compressionopen access
- Authors
- Ko, Jong Hwan; Kim, Sang Hoon
- Issue Date
- 1-Sep-2023
- Publisher
- Institute of Electronics Information Communication Engineers
- Keywords
- acceleration; adaptive; channel-scheduling; fine-control; RNN; target-dependent
- Citation
- IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, v.E106.A, no.9, pp 1211 - 1215
- Pages
- 5
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Volume
- E106.A
- Number
- 9
- Start Page
- 1211
- End Page
- 1215
- URI
- https://scholarworks.bwise.kr/skku/handle/2021.sw.skku/108386
- DOI
- 10.1587/transfun.2022IML0001
- ISSN
- 0916-8508
1745-1337
- Abstract
- SUMMARY The existing target-dependent scalable image compression network can control the target of the compressed images between the human visual system and the deep learning based classification task. However, in its RNN based structure controls the bit-rate through the number of iterations, where each iteration generates a fixed size of the bit stream. Therefore, a large number of iterations are required at the high BPP, and fine-grained image quality control is not supported at the low BPP. In this paper, we propose a novel RNN-based image compression model that can schedule the channel size per iteration, to reduce the number of iterations at the high BPP and fine-grained bit-rate control at the low BPP. To further enhance the efficiency, multiple network models for various channel sizes are combined into a single model using the slimmable network architecture. The experimental results show that the proposed method achieves comparable performance to the existing method with finer BPP adjustment, increases parameters by only 0.15% and reduces the average amount of computation by 40.4%. Copyright © 2023 The Institute of Electronics, Information and Communication Engineers.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Information and Communication Engineering > School of Electronic and Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.