LEARNED IMAGE COMPRESSION WITH SOFT BIT-BASED RATE-DISTORTION OPTIMIZATION
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
1719 | en_US |
dc.citation.spage |
1715 | en_US |
dc.citation.woscount |
0 | en_US |
dc.contributor.author |
Alexandre, David | en_US |
dc.contributor.author |
Chang, Chih-Peng | en_US |
dc.contributor.author |
Peng, Wen-Hsiao | en_US |
dc.contributor.author |
Hang, Hsueh-Ming | en_US |
dc.contributor.department |
交大名義發表 | zh_TW |
dc.contributor.department |
資訊工程學系 | zh_TW |
dc.contributor.department |
電子工程學系及電子研究所 | zh_TW |
dc.contributor.department |
National Chiao Tung University | en_US |
dc.contributor.department |
Department of Computer Science | en_US |
dc.contributor.department |
Department of Electronics Engineering and Institute of Electronics | en_US |
dc.date.accessioned |
2020-05-05T00:01:59Z | |
dc.date.available |
2020-05-05T00:01:59Z | |
dc.date.issued |
2019-01-01 | en_US |
dc.description.abstract |
This paper introduces the notion of soft bits to address the rate-distortion optimization for learning-based image compression. Recent methods for such compression train an autoencoder end-to-end with an objective to strike a balance between distortion and rate. They are faced with the zero gradient issue due to quantization and the difficulty of estimating the rate accurately. Inspired by soft quantization, we represent quantization indices of feature maps with differentiable soft bits. This allows us to couple tightly the rate estimation with context-adaptive binary arithmetic coding. It also provides a differentiable distortion objective function. Experimental results show that our approach achieves the state-of-the-art compression performance among the learning-based schemes in terms of MS-SSIM and PSNR. | en_US |
dc.identifier.isbn |
978-1-5386-6249-6 | en_US |
dc.identifier.issn |
1522-4880 | en_US |
dc.identifier.journal |
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/154043 | |
dc.identifier.wosnumber |
WOS:000521828601169 | en_US |
dc.language.iso |
en_US | en_US |
dc.subject |
Autoencoder | en_US |
dc.subject |
Deep Learning | en_US |
dc.subject |
Image Compression | en_US |
dc.subject |
Soft Bits | en_US |
dc.title |
LEARNED IMAGE COMPRESSION WITH SOFT BIT-BASED RATE-DISTORTION OPTIMIZATION | en_US |
dc.type |
Proceedings Paper | en_US |
檔案
本條目沒有附加檔案。
所屬典藏: 會議論文
引用此條目
Alexandre, D., Chang, C.-P., Peng, W.-H., & Hang, H.-M. (2019). LEARNED IMAGE COMPRESSION WITH SOFT BIT-BASED RATE-DISTORTION OPTIMIZATION. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 1715–1719. https://ir.lib.nycu.edu.tw/handle/11536/154043
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/154043