• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Adaptive Importance Channel Selection for Perceptual Image Compression

Vol. 14, No. 9, September 30, 2020
10.3837/tiis.2020.09.014, Download Paper (Free):

Abstract

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
Y. He, F. Li, H. Bai and Y. Zhao, "Adaptive Importance Channel Selection for Perceptual Image Compression," KSII Transactions on Internet and Information Systems, vol. 14, no. 9, pp. 3823-3840, 2020. DOI: 10.3837/tiis.2020.09.014.

[ACM Style]
Yifan He, Feng Li, Huihui Bai, and Yao Zhao. 2020. Adaptive Importance Channel Selection for Perceptual Image Compression. KSII Transactions on Internet and Information Systems, 14, 9, (2020), 3823-3840. DOI: 10.3837/tiis.2020.09.014.

[BibTeX Style]
@article{tiis:23863, title="Adaptive Importance Channel Selection for Perceptual Image Compression", author="Yifan He and Feng Li and Huihui Bai and Yao Zhao and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2020.09.014}, volume={14}, number={9}, year="2020", month={September}, pages={3823-3840}}