# Analyzing and Mitigating JPEG Compression Defects in Deep Learning

arXiv: https://arxiv.org/abs/2011.08932 · HTML: https://mlsanity.com/paper/2011.08932/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [Leveraging Bitstream Metadata for Fast, Accurate, Generalized Compressed Video Quality Enhancement](https://mlsanity.com/paper/2202.00011/) (2022)
- [Leveraging the Edge and Cloud for V2X-Based Real-Time Object Detection in Autonomous Driving](https://mlsanity.com/paper/2308.05234/) (2023)
- [Processing and acquisition traces in visual encoders: What does CLIP know about your camera?](https://mlsanity.com/paper/2508.10637/) (2025)
- [Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training](https://mlsanity.com/paper/2208.07075/) (2022)
- [CNNs for JPEGs: A Study in Computational Cost](https://mlsanity.com/paper/2309.11417/) (2023)
- [Gait Recognition from Highly Compressed Videos](https://mlsanity.com/paper/2404.12183/) (2024)

## Abstract (arXiv)

With the proliferation of deep learning methods, many computer vision problems which were considered academic are now viable in the consumer setting. One drawback of consumer applications is lossy compression, which is necessary from an engineering standpoint to efficiently and cheaply store and transmit user images. Despite this, there has been little study of the effect of compression on deep neural networks and benchmark datasets are often losslessly compressed or compressed at high quality. Here we present a unified study of the effects of JPEG compression on a range of common tasks and datasets. We show that there is a significant penalty on common performance metrics for high compression. We test several methods for mitigating this penalty, including a novel method based on artifact correction which requires no labels to train.