Browse > Article
http://dx.doi.org/10.3837/tiis.2020.09.014

Adaptive Importance Channel Selection for Perceptual Image Compression  

He, Yifan (Institute of Information Science, Beijing Jiaotong University)
Li, Feng (Institute of Information Science, Beijing Jiaotong University)
Bai, Huihui (Institute of Information Science, Beijing Jiaotong University)
Zhao, Yao (Institute of Information Science, Beijing Jiaotong University)
Publication Information
KSII Transactions on Internet and Information Systems (TIIS) / v.14, no.9, 2020 , pp. 3823-3840 More about this Journal
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.
Keywords
Image compression; Auto-encoder; Perceptual loss; Bit-allocate strategy; Importance map;
Citations & Related Records
연도 인용수 순위
  • Reference
1 G. K. Wallace, "The jpeg still picture compression standard," IEEE transactions on consumer electronics, 38(1), xviii- xxxiv, 1992.   DOI
2 A. Skodras, C. Christopoulos, and T. Ebrahimi, "The jpeg 2000 still image compression standard," IEEE Signal processing magazine, 18(5), 36-58, 2001.   DOI
3 F. Bellard, "BPG Image Format," 2014. Accessed: 2017-01-30.
4 J. Lainema, F. Bossen, W.-J. Han, J. Min, and K. Ugur, "Intra coding of the HEVC standard," IEEE Trans. Circuits Syst. Video Technol., vol. 22, no. 12, pp. 1792-1801, Dec. 2012.   DOI
5 F. Li, H. Bai, Y. Zhao, "FilterNet: Adaptive Information Filtering Network for Accurate and Fast Image Super-Resolution," IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 6, pp. 1511-1523, 2019.   DOI
6 J. Kim, J. Kwon Lee, K. Mu Lee, "Accurate image super-resolution using very deep convolutional networks," in Proc. of the IEEE conference on computer vision and pattern recognition, 1646-1654, 2016.
7 M. Li, W. Zuo, S. Gu, et al., "Learning convolutional networks for content-weighted image compression," in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 3214-3223, 2018.
8 F. Mentzer, E. Agustsson, M. Tschannen, et al., "Practical full resolution learned lossless image compression," in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 10629-10638, 2019.
9 J. Balle, V. Laparra, and E. P. Simoncelli, "End-to-end optimized image compression," in Proc. of International Conference on Learning Representations, 2017.
10 F. Mentzer, E. Agustsson, M. Tschannen, et al., "Conditional probability models for deep image compression," in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 4394-4402, 2018.
11 G. Toderici, D. Vincent, N. Johnston, et al., "Full resolution image compression with recurrent neural networks," in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 5306-5314, 2017.
12 D. E. Rumelhart, G. E. Hinton, R. J. Williams. "Learning internal representations by error propagation," California Univ San Diego La Jolla Inst for Cognitive Science, 1985.
13 S. Santurkar, D. Budden, N. Shavit. "Generative compression," in Proc. of Picture Coding Symposium. IEEE, 258-262, 2018.
14 Y. LeCun, B. E. Boser, J. S. Denker, et al., "Handwritten digit recognition with a back-propagation network," in Proc. of Advances in neural information processing systems, 396-404, 1990.
15 L Theis, W Shi, A Cunningham, F Huszar, "Lossy image compression with compressive autoencoders," in Proc. of International Conference on Learning Representations, 2017.
16 T. Dumas, A. Roumy, C. Guillemot. "Autoencoder based image compression: can the learning be quantization independent?," in Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, 1188-1192, 2018.
17 K. M. Nakanishi, S. Maeda, T. Miyato, et al., "Neural multi-scale image compression," in Proc. of Asian Conference on Computer Vision. Springer, Cham, 718-732, 2018.
18 N. Johnston, D. Vincent, D. Minnen, et al., "Improved lossy image compression with priming and spatially adaptive bit rates for recurrent networks," in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 4385-4393, 2018.
19 D. P. Kingma, M. Welling. "Auto-encoding variational bayes," in Proc. of International Conference on Learning Representations, 2014.
20 E. Agustsson, M. Tschannen, F. Mentzer, et al., "Generative adversarial networks for extreme learned image compression," in Proc. of the IEEE International Conference on Computer Vision, 221-231, 2019.
21 J. Johnson, A. Alahi, L. Fei-Fei. "Perceptual losses for real-time style transfer and super-resolution," in Proc. of European conference on computer vision. Springer, Cham, 694-711, 2016.
22 M Jian, KM Lam, J Dong, et al., "Visual-patch-attention-aware Saliency Detection," IEEE Transactions on Cybernetics, Vol. 45, No. 8, pp. 1575-1586, 2015.   DOI
23 J. Balle. "Efficient nonlinear transforms for lossy image compression," in Proc. of Picture Coding Symposium. IEEE, 248-252, 2018.
24 M Jian, W zhang, Y Hui, et al., "Saliency detection based on directional patches extraction and principal local color contrast," Journal of Visual Communication and Image Representation, Vol. 57, pp. 1-11, 2018.   DOI
25 J. Deng, W. Dong, R. Socher, et al., "Imagenet: A large-scale hierarchical image database," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 248-255, 2019.
26 Kodak PhotoCD dataset.
27 J. Balle, D Minnen, S Singh, et al., "Variational image compression with a scale hyperprior," in Proc. of International Conference on Learning Representations, 2018.
28 Z. Wang, E. P. Simoncelli, A. C. Bovik, "Multiscale structural similarity for image quality assessment," in Proc. of The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2, 1398-1402, 2003.
29 J. Lee, S. Cho, S. K. Beack. "Context-adaptive entropy model for end-to-end optimized image compression," in Proc. of International Conference on Learning Representations, 2019.