# On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures

arXiv: https://arxiv.org/abs/2007.14314 · HTML: https://mlsanity.com/paper/2007.14314/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2020.

## Built on by (most cited first, 11 of 11)

- [Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond](https://mlsanity.com/paper/2104.01493/) (2021)
- [Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery](https://mlsanity.com/paper/2205.08002/) (2022)
- [Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-Ray Imagery](https://mlsanity.com/paper/2110.04906/) (2021)
- [Does lossy image compression affect racial bias within face recognition?](https://mlsanity.com/paper/2208.07613/) (2022)
- [Data Models for Dataset Drift Controls in Machine Learning With Optical Images](https://mlsanity.com/paper/2211.02578/) (2022)
- [Impact of Video Compression on the Performance of Object Detection Systems for Surveillance Applications](https://mlsanity.com/paper/2211.05805/) (2022)
- [Drone Detection using Deep Neural Networks Trained on Pure Synthetic Data](https://mlsanity.com/paper/2411.09077/) (2024)
- [Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling](https://mlsanity.com/paper/2606.15959/) (2026)
- [TACTIC: Joint Rate-Distortion-Accuracy Optimisation for Low Bitrate Compression](https://mlsanity.com/paper/2109.10658/) (2021)
- [Impact of Video Compression Artifacts on Fisheye Camera Visual Perception Tasks](https://mlsanity.com/paper/2403.16338/) (2024)
- [BLUE: Semantics-Preserving Video Compression for Efficient Vision-Language Surveillance Analytics](https://mlsanity.com/paper/2607.19515/) (2026)

## Abstract (arXiv)

Recent advances in generalized image understanding have seen a surge in the use of deep convolutional neural networks (CNN) across a broad range of image-based detection, classification and prediction tasks. Whilst the reported performance of these approaches is impressive, this study investigates the hitherto unapproached question of the impact of commonplace image and video compression techniques on the performance of such deep learning architectures. Focusing on the JPEG and H.264 (MPEG-4 AVC) as a representative proxy for contemporary lossy image/video compression techniques that are in common use within network-connected image/video devices and infrastructure, we examine the impact on performance across five discrete tasks: human pose estimation, semantic segmentation, object detection, action recognition, and monocular depth estimation. As such, within this study we include a variety of network architectures and domains spanning end-to-end convolution, encoder-decoder, region-based CNN (R-CNN), dual-stream, and generative adversarial networks (GAN). Our results show a non-linear and non-uniform relationship between network performance and the level of lossy compression applied. Notably, performance decreases significantly below a JPEG quality (quantization) level of 15% and a H.264 Constant Rate Factor (CRF) of 40. However, retraining said architectures on pre-compressed imagery conversely recovers network performance by up to 78.4% in some cases. Furthermore, there is a correlation between architectures employing an encoder-decoder pipeline and those that demonstrate resilience to lossy image compression. The characteristics of the relationship between input compression to output task performance can be used to inform design decisions within future image/video devices and infrastructure.