# Semantic-assisted image compression

Source: [Semantic-assisted image compression](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff76>)

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

Data updated: 2025-10-25T23:56:05.140Z

Authors: Qizheng Sun, Caili Guo, Yang Yang, Jiujiu Chen, Xijun Xue (2) \_\_INSTITUTION\_5\_\_ bupt.edu.cn, (2) chinatelecom.cn )

Published: 2022-01-29T14:49:30.000Z

## Abstract

Conventional image compression methods typically aim at pixel-level consistency while ignoring the performance of downstream AI tasks.To solve this problem, this paper proposes a Semantic-Assisted Image Compression method (SAIC), which can maintain semantic-level consistency to enable high performance of downstream AI tasks.To this end, we train the compression network using semantic-level loss function. In particular, semantic-level loss is measured using gradient-based semantic weights mechanism (GSW). GSW directly consider downstream AI tasks' perceptual results. Then, this paper proposes a semantic-level distortion evaluation metric to quantify the amount of semantic information retained during the compression process. Experimental results show that the proposed SAIC method can retain more semantic-level information and achieve better performance of downstream AI tasks compared to the traditional deep learning-based method and the advanced perceptual method at the same compression ratio.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2201.12599>)

[PDF](<https://arxiv.org/pdf/2201.12599.pdf>)
