# Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery

arXiv: https://arxiv.org/abs/2205.08002 · HTML: https://mlsanity.com/paper/2205.08002/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 16 May 2022.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [Feature Selective Anchor-Free Module for Single-Shot Object Detection](https://mlsanity.com/paper/1903.00621/) (2019)
- [Understanding How Image Quality Affects Deep Neural Networks](https://mlsanity.com/paper/1604.04004/) (2016)
- [Multispectral Deep Neural Networks for Pedestrian Detection](https://mlsanity.com/paper/1611.02644/) (2016)
- [Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery](https://mlsanity.com/paper/1905.08789/) (2019)
- [SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving](https://mlsanity.com/paper/2103.03150/) (2021)
- [On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures](https://mlsanity.com/paper/2007.14314/) (2020)
- [Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-Ray Imagery](https://mlsanity.com/paper/2110.04906/) (2021)

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

- [1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results](https://mlsanity.com/paper/2211.13508/) (2022)
- [Data Quality Matters: Quantifying Image Quality Impact on Machine Learning Performance](https://mlsanity.com/paper/2503.22375/) (2025)
- [Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark](https://mlsanity.com/paper/2510.09343/) (2025)
- [Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery](https://mlsanity.com/paper/2404.12285/) (2024)
- [JPEG Compliant Compression for Both Human and Machine, A Report](https://mlsanity.com/paper/2503.10912/) (2025)
- [Learned JPEG Compression for DNN Vision](https://mlsanity.com/paper/2606.16185/) (2026)

## Abstract (arXiv)

Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such compression can cause severe decline in performance of deep Convolution Neural Network (CNN) architectures even when mild compression is applied and the resulting compressed imagery is visually identical. In this work, we apply the lossy JPEG compression method with six discrete levels of increasing compression {95, 75, 50, 15, 10, 5} to infrared band (thermal) imagery. Our study quantitatively evaluates the affect that increasing levels of lossy compression has upon the performance of characteristically diverse object detection architectures (Cascade-RCNN, FSAF and Deformable DETR) with respect to varying sizes of objects present in the dataset. When training and evaluating on uncompressed data as a baseline, we achieve maximal mean Average Precision (mAP) of 0.823 with Cascade R-CNN across the FLIR dataset, outperforming prior work. The impact of the lossy compression is more extreme at higher compression levels (15, 10, 5) across all three CNN architectures. However, re-training models on lossy compressed imagery notably ameliorated performances for all three CNN models with an average increment of ~76% (at higher compression level 5). Additionally, we demonstrate the relative sensitivity of differing object areas {tiny, small, medium, large} with respect to the compression level. We show that tiny and small objects are more sensitive to compression than medium and large objects. Overall, Cascade R-CNN attains the maximal mAP across most of the object area categories.