Deep reconstruction of 1D ISOMAP representations
Abstract
This paper proposes a deep learning priors-based data reconstruction method of 1D isometric feature mapping (ISOMAP) representations. ISOMAP is a classical algorithm of nonlinear dimensionality reduction (NLDR) or manifold leaning (ML), which is devoted to questing for the low dimensional structure of high dimensional data. The reconstruction of ISOMAP representations, or the inverse problem of ISOMAP, reestablishes the high dimensional data from its low dimensional ISOMAP representations, and owns a bright future in data representation, generation, compression and visualization. Due to the fact that the dimension of ISOMAP representations is far less than that of the original high dimensional data, the reconstruction of ISOMAP representations is ill-posed or undetermined. Hence, the residual learning of deep convolutional neural network (CNN) is employed to boost reconstruction performance, via achieving the priors between the low-quality result of general ISOMAP reconstruction method and its residual relative to the original data. In the situation of 1D representations, it is evaluated by the experimental results that the proposed method outbalances the state-of-the-art methods, such as nearest neighbor (NN), discrete cosine transformation (DCT) and sparse representation (SR), in reconstruction performance of video data. In summary, the proposed method is suitable for low-bitrate and high-performance applications of data reconstruction.
References
[1]
Xian W, Hao S, and Yuanxiang Li Reconstructible nonlinear dimensionality reduction via joint dictionary learning IEEE Trans. Neural Netw. Learn. Syst. 2018 30 1 175-189
[2]
Tenenbaum JB, de Silva V, and Langford JC A global geometric framework for nonlinear dimensionality reduction Science 2000 290 5500 2319-2323
[3]
Zhu B, Liu JZ, and Cauley SF Image reconstruction by domain-transform manifold learning Nature 2018 555 7697 487
[4]
Zhang K, Zuo W, Chen Y, Meng D, and Zhang L Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising IEEE Trans. Image Process. 2017 26 7 3142-3155
[5]
Zhang L and Zuo W Image restoration: from sparse and low-rank priors to deep priors IEEE Signal Process. Mag. 2017 34 5 172-179
[6]
Li H 1D representation of Isomap for united video coding Multimedia Syst. 2018 24 3 297-312
[7]
Kai Z, Wangmeng Z, and Lei Z FFDNet: toward a fast and flexible solution for CNN-based image denoising IEEE Trans. Image Process. 2018 27 9 4608-4622
[8]
Li, J., Yu, J., Xu, L.: A cascaded algorithm for image quality assessment and image denoising based on CNN for image security and authorization. Secur. Commun. Netw. Article Number: UNSP 8176984 (2018).
[9]
Yuan Y, Cao Z, and Su L Light-field image superresolution using a combined deep CNN based on EPI IEEE Signal Process. Lett. 2018 25 9 1359-1363
[10]
Ren C, He X, and Pu Y Nonlocal similarity modeling and deep CNN gradient prior for super resolution IEEE Signal Process. Lett. 2018 25 7 916-920
[11]
Zhang M, Li W, and Du Q Diverse region-based CNN for hyperspectral image classification IEEE Trans. Image Process. 2018 27 6 2623-2634
[12]
Guo Y, Liu Y, and Bakker EM EM CNN-RNN: a large-scale hierarchical image classification framework Multimed. Tools Appl. 2018 77 8 10251-10271
[13]
Li, J., Qiu, T., Wen, C.: Robust face recognition using the deep C2D-CNN model based on decision-level fusion, Sensors 18(7), Article Number: 2080 (2018)
[14]
He R, Wu X, and Sun Z Wasserstein CNN: learning invariant features for NIR-VIS face recognition IEEE Trans. Pattern Anal. Mach. Intell. 2019 41 7 1761-1773
[15]
Chenggang Y, Biao G, Yuxuan W, and Yue G Deep Multi-view enhancement hashing for image retrieval IEEE Trans. Pattern Anal. Mach. Intell. 2020
[16]
Yan C, Shao B, Zhao H, Ning R, Zhang Y, and Feng Xu 3D room layout estimation from a single RGB image IEEE Trans. Multimed. 2020 22 11 3104-3124
[17]
Chenggang, Y., Zhisheng, L., Yongbing, Z., Yutao, L., Xiangyang J., Yongdong Z.: Depth image denoising using nuclear norm and learning graph model. ACM Trans. Multimed. Comput. Commun. Appl. pp. 1–17. Preprint at arXiv:2008.03741v1[cs.CV] (2020)
[18]
Weiying X, Yunsong Li, and Xiuping J Deep convolutional networks with residual learning for accurate spectral-spatial denoising Neurocomputing 2018 312 372-381
[19]
Chen, C., Xu, Z.: Aerial-image denoising based on convolutional neural network with multi-scale residual learning approach. Information. 9(7), Article Number: UNSP 169 (2018).
[20]
Zhang Y, MacDougall R, and Yu H Residual learning based projection domain denoising for low-dose CT Med. Phys. 2018 45 6 E215-E216
[21]
Zhan, Q., Yuan, Q., Li, J.: Learning a dilated residual network for SAR image despeckling. Remote Sens. 10(2), Article Number: 196 (2018).
[22]
Shi, J., Liu, Q., Wang, C.: Super-resolution reconstruction of MR image with a novel residual learning network algorithm. Phys. Med. Biol. 63(8), Article Number: 085011 (2018).
[23]
Wenjun W, Chao R, and Xiaohai He Video super-resolution via residual learning IEEE Access 2018 6 23767-23777
[24]
Dingyi L and Zengfu W Video superresolution via motion compensation and deep residual learning IEEE Trans. Comput. Imaging 2017 3 4 749-762
[25]
Wenhan Y, Jiashi F, and Jianchao Y Deep edge guided recurrent residual learning for image super-resolution IEEE Trans. Image Process. 2017 26 12 5895-5907
[26]
Feiwei Q, Nannan G, and Yong P Fine-grained leukocyte classification with deep residual learning for microscopic images Comput. Methods Programs Biomed. 2018 162 243-252
[27]
Haijun L, Tao H, and Feng Z A deeply supervised residual network for HEp-2 cell classification via cross-modal transfer learning Pattern Recogn. 2018 79 290-302
[28]
McAllister P, Zheng H, and Bond R Combining deep residual neural network features with supervised machine learning algorithms to classify diverse food image datasets Comput. Biol. Med. 2018 95 217-233
[29]
Zilong Z, Jonathan Li, and Zhiming L Spectral-spatial residual network for hyperspectral image classification: a 3-D deep learning framework IEEE Trans. Geosci. Remote Sens. 2018 56 2 847-858
[30]
Mou L, Ghamisi P, and Zhu XX Unsupervised spectral-spatial feature learning via deep residual conv-deconv network for hyperspectral image classification IEEE Trans. Geosci. Remote Sending 2018 56 1 391-406
[31]
Xi C, Youhua Z, and Yiqiong C Pest identification via deep residual learning in complex background Comput. Electron. Agric. 2017 141 351-356
[32]
Yancong W, Qiangqiang Y, and Huanfeng S Boosting the accuracy of multispectral image pansharpening by learning a deep residual network IEEE Geosci. Remote Sens. Lett. 2017 14 10 1795-1799
[33]
Songtao W, Shenghua Z, and Yan L Deep residual learning for image steganalysis Multimed. Tools Appl. 2018 77 9 10437-10453
[34]
Devalla SK, Renukanand PK, and Sreedhar BK DRUNET: a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images Biomed. Opt. Express 2018 9 7 3244-3265
[35]
Yang-Yu F, Shu L, and Bo Li Label distribution-based facial attractiveness computation by deep residual learning IEEE Trans. Multimed. 2018 20 8 2196-2208
[36]
Sullivan GJ, Ohm J-R, Han W-J, and Wiegand T Overview of the high efficiency video coding (HEVC) standard IEEE Trans. Circuits Syst. Video Technol. 2012 22 12 1649-1668
[37]
van der Maaten LJP and Hinton GE Visualizing high-dimensional data using t-SNE J. Mach. Learn. Res. 2008 9 2 2579-2605
Recommendations
Nonlinear dimensionality reduction by locally linear inlaying
High-dimensional data is involved in many fields of information processing. However, sometimes, the intrinsic structures of these data can be described by a few degrees of freedom. To discover these degrees of freedom or the low-dimensional nonlinear ...
Multi-manifold Discriminant Isomap for visualization and classification
Isomap aims to recover the intrinsic geometric structure of manifold by preserving geodesic distances between all pairs of data points. However it is an unsupervised dimensionality-reduction method. Usually, using class label information can increase ...
1D representation of Isomap for united video coding
This paper proposes a 1D representation of isometric feature mapping (Isomap) based united video coding algorithms. First, 1D Isomap representations that maintain distances are generated which can achieve a very high compression ratio. Next, embedding ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature 2021.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 June 2021
Accepted: 04 January 2021
Received: 26 November 2019
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 10 Feb 2025