# Semantic-assisted image compression

arXiv: https://arxiv.org/abs/2201.12599 · HTML: https://mlsanity.com/paper/2201.12599/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 15 references that are in the map.
- First posted on arXiv 29 Jan 2022.

## Builds on (most cited first, 8 of 8)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Context-adaptive Entropy Model for End-to-end Optimized Image Compression](https://mlsanity.com/paper/1809.10452/) (2018)
- [Receptive Field Block Net for Accurate and Fast Object Detection](https://mlsanity.com/paper/1711.07767/) (2017)
- [Learning Convolutional Networks for Content-weighted Image Compression](https://mlsanity.com/paper/1703.10553/) (2017)
- [Deep Convolutional AutoEncoder-based Lossy Image Compression](https://mlsanity.com/paper/1804.09535/) (2018)
- [A GAN-based Tunable Image Compression System](https://mlsanity.com/paper/2001.06580/) (2020)

## Abstract (arXiv)

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.