An Autoencoder-Based Learned Image Compressor: Description of Challenge Proposal by NCTU
Abstract
We propose a lossy image compression system using the deep-learning autoencoder structure to participate in the Challenge on Learned Image Compression (CLIC) 2018. Our autoencoder uses the residual blocks with skip connections to reduce the correlation among image pixels and condense the input image into a set of feature maps, a compact representation of the original image. The bit allocation and bitrate control are implemented by using the importance maps and quantizer. The importance maps are generated by a separate neural net in the encoder. The autoencoder and the importance net are trained jointly based on minimizing a weighted sum of mean squared error, MS-SSIM, and a rate estimate. Our aim is to produce reconstructed images with good subjective quality subject to the 0.15 bits per-pixel constraint.
Cite
Text
Alexandre et al. "An Autoencoder-Based Learned Image Compressor: Description of Challenge Proposal by NCTU." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.Markdown
[Alexandre et al. "An Autoencoder-Based Learned Image Compressor: Description of Challenge Proposal by NCTU." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/alexandre2018cvprw-autoencoderbased/)BibTeX
@inproceedings{alexandre2018cvprw-autoencoderbased,
title = {{An Autoencoder-Based Learned Image Compressor: Description of Challenge Proposal by NCTU}},
author = {Alexandre, David and Chang, Chih-Peng and Peng, Wen-Hsiao and Hang, Hsueh-Ming},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2018},
pages = {2539-2542},
url = {https://mlanthology.org/cvprw/2018/alexandre2018cvprw-autoencoderbased/}
}