Corpus ID: 235694726

Cascade Decoders-Based Autoencoders for Image Reconstruction

@article{Li2021CascadeDA,
  title={Cascade Decoders-Based Autoencoders for Image Reconstruction},
  author={Honggui Li and Dimitri Galayko and Maria Trocan and Mohamad Sawan},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.00002}
}
Autoencoders are composed of coding and decoding units, hence they hold the inherent potential of high-performance data compression and signal compressed sensing. The main disadvantages of current autoencoders comprise the following several aspects: the research objective is not data reconstruction but feature representation; the performance evaluation of data recovery is neglected; it is hard to achieve lossless data reconstruction by pure autoencoders, even by pure deep learning. This paper… Expand

References

SHOWING 1-10 OF 27 REFERENCES
Deep Residual Learning-based Reconstruction of Stacked Autoencoder Representation
  • Honggui Li, M. Trocan
  • Computer Science
  • 2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS)
  • 2018
TLDR
It is demonstrated by experimental results that deep CNN is superior to SAE decoder in rebuilding the performance of image data and can be employed for low-bitrate and high-quality data compression. Expand
An autoencoder based formulation for compressed sensing reconstruction.
  • A. Majumdar
  • Medicine, Computer Science
  • Magnetic resonance imaging
  • 2018
TLDR
Experimental studies on MRI reconstruction shows that the proposed method outperforms state-of-the-art methods in dictionary learning, transform learning and (non-adaptive) autoencoder based approaches. Expand
DVC: An End-To-End Deep Video Compression Framework
TLDR
This paper proposes the first end-to-end video compression deep model that jointly optimizes all the components for video compression, and shows that the proposed approach can outperform the widely used video coding standard H.264 in terms of PSNR and be even on par with the latest standard MS-SSIM. Expand
Autoencoder With Invertible Functions for Dimension Reduction and Image Reconstruction
TLDR
Unlike existing multilayer ELM, in this paper all hidden layers with invertible functions are calculated by pulling the network output back and putting it into hidden layers, which results in much better learning efficiency than DL. Expand
A Technical Analysis on Deep Learning based Image and Video Compression
In this paper, we investigate image and video compression techniques based on deep learning which are actively studied recently. The deep learning based image compression technique inputs an image toExpand
Fully Connected Network-Based Intra Prediction for Image Coding
TLDR
This paper proposes using a fully connected network to learn an end-to-end mapping from neighboring reconstructed pixels to the current block to generate better prediction using traditional single line-based methods. Expand
Blind Denoising Autoencoder
  • A. Majumdar
  • Engineering, Computer Science
  • IEEE Transactions on Neural Networks and Learning Systems
  • 2019
TLDR
Experimental results show that the proposed method performs better than dictionary learning (K-singular value decomposition), transform learning, sparse stacked denoising autoencoder, and the gold standard BM3D algorithm. Expand
Semi-supervised Stacked Label Consistent Autoencoder for Reconstruction and Analysis of Biomedical Signals
TLDR
This is the first study offering an alternative to CS-based reconstruction and shows that the representation learning approach can yield better results than traditional methods that use hand-crafted features for signal analysis. Expand
Deep Compressive Autoencoder for Action Potential Compression in Large-Scale Neural Recording
TLDR
A deep learning-based compression model to reduce the required data transmission bandwidth in large-scale recording experiments and maintain good signal qualities, which will be helpful to design power-efficient and lightweight wireless neural interfaces. Expand
Efficient Compressed Sensing for Wireless Neural Recording: A Deep Learning Approach
TLDR
A binarized autoencoder scheme for CS is presented, in which a binary sensing matrix and a noniterative recovery solver are jointly optimized, which outperforms the state-of-the-art CS-based methods both in terms of recovery quality and computation time. Expand
...
1
2
3
...