# Convolutional Neural Network (CNN) to reduce construction loss in JPEG compression caused by Discrete Fourier Transform (DFT)

arXiv: https://arxiv.org/abs/2209.03475 · HTML: https://mlsanity.com/paper/2209.03475/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 26 Aug 2022.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overfitting in adversarially robust deep learning](https://mlsanity.com/paper/2002.11569/) (2020)
- [How Does Batch Normalization Help Optimization?](https://mlsanity.com/paper/1805.11604/) (2018)
- [Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark](https://mlsanity.com/paper/2109.14545/) (2021)
- [Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks](https://mlsanity.com/paper/2006.07322/) (2020)
- [Deep Convolutional AutoEncoder-based Lossy Image Compression](https://mlsanity.com/paper/1804.09535/) (2018)
- [Generative Compression](https://mlsanity.com/paper/1703.01467/) (2017)
- [Introducing Hann windows for reducing edge-effects in patch-based image segmentation](https://mlsanity.com/paper/1910.07831/) (2019)
- [Compression Artifacts Removal Using Convolutional Neural Networks](https://mlsanity.com/paper/1605.00366/) (2016)
- [Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removal](https://mlsanity.com/paper/2009.06912/) (2020)
- [Adaptive Learning Rate Clipping Stabilizes Learning](https://mlsanity.com/paper/1906.09060/) (2019)
- [A survey on recently proposed activation functions for Deep Learning](https://mlsanity.com/paper/2204.02921/) (2022)
- [An Autoencoder-based Learned Image Compressor: Description of Challenge Proposal by NCTU](https://mlsanity.com/paper/1902.07385/) (2019)
- [Attention-based Image Upsampling](https://mlsanity.com/paper/2012.09904/) (2020)
- [Learning to Inpaint for Image Compression](https://mlsanity.com/paper/1709.08855/) (2017)
- [On the Regularization of Autoencoders](https://mlsanity.com/paper/2110.11402/) (2021)

## Abstract (arXiv)

In recent decades, digital image processing has gained enormous popularity. Consequently, a number of data compression strategies have been put forth, with the goal of minimizing the amount of information required to represent images. Among them, JPEG compression is one of the most popular methods that has been widely applied in multimedia and digital applications. The periodic nature of DFT makes it impossible to meet the periodic condition of an image's opposing edges without producing severe artifacts, which lowers the image's perceptual visual quality. On the other hand, deep learning has recently achieved outstanding results for applications like speech recognition, image reduction, and natural language processing. Convolutional Neural Networks (CNN) have received more attention than most other types of deep neural networks. The use of convolution in feature extraction results in a less redundant feature map and a smaller dataset, both of which are crucial for image compression. In this work, an effective image compression method is purposed using autoencoders. The study's findings revealed a number of important trends that suggested better reconstruction along with good compression can be achieved using autoencoders.