# Expanded Adaptive Scaling Normalization for End to End Image Compression

Source: [Expanded Adaptive Scaling Normalization for End to End Image Compression](<https://www.sota2.com/research/paper/68fa7fc51e209131cea9b098>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T06:52:33.836Z

Authors: Chajin Shin, Hyeongmin Lee, Hanbin Son, Sangjin Lee, Dogyoon Lee, Sangyoun Lee

Published: 2022-08-05T09:05:24.000Z

## Abstract

Recently, learning-based image compression methods that utilize convolutional neural layers have been developed rapidly. Rescaling modules such as batch normalization which are often used in convolutional neural networks do not operate adaptively for the various inputs. Therefore, Generalized Divisible Normalization(GDN) has been widely used in image compression to rescale the input features adaptively across both spatial and channel axes. However, the representation power or degree of freedom of GDN is severely limited. Additionally, GDN cannot consider the spatial correlation of an image. To handle the limitations of GDN, we construct an expanded form of the adaptive scaling module, named Expanded Adaptive Scaling Normalization(EASN). First, we exploit the swish function to increase the representation ability. Then, we increase the receptive field to make the adaptive rescaling module consider the spatial correlation. Furthermore, we introduce an input mapping function to give the module a higher degree of freedom. We demonstrate how our EASN works in an image compression network using the visualization results of the feature map, and we conduct extensive experiments to show that our EASN increases the rate-distortion performance remarkably, and even outperforms the VVC intra at a high bit rate.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Lossy Image Compression on Wind turbine image dataset full-resolution](<https://www.sota2.com/research/sota/lossy-image-compression-on-wind-turbine-image-dataset-full-resolution.md>): Lossy Image Compression; Wind turbine image dataset full-resolution; BD-rate (PSNR): 2.14.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2208.03049>)

[PDF](<https://arxiv.org/pdf/2208.03049.pdf>)
