# Training CNNs in Presence of JPEG Compression: Multimedia Forensics vs Computer Vision

arXiv: https://arxiv.org/abs/2009.12088 · HTML: https://mlsanity.com/paper/2009.12088/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 17 of 17)

- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [Detecting GAN-generated Images by Orthogonal Training of Multiple CNNs](https://mlsanity.com/paper/2203.02246/) (2022)
- [CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning](https://mlsanity.com/paper/2112.00686/) (2021)
- [AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images](https://mlsanity.com/paper/2404.14244/) (2024)
- [VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces](https://mlsanity.com/paper/2211.15775/) (2022)
- [Towards the Detection of AI-Synthesized Human Face Images](https://mlsanity.com/paper/2402.08750/) (2024)
- [When Synthetic Traces Hide Real Content: Analysis of Stable Diffusion Image Laundering](https://mlsanity.com/paper/2407.10736/) (2024)
- [Is JPEG AI going to change image forensics?](https://mlsanity.com/paper/2412.03261/) (2024)
- [An Overview on the Generation and Detection of Synthetic and Manipulated Satellite Images](https://mlsanity.com/paper/2209.08984/) (2022)
- [Amplitude SAR Imagery Splicing Localization](https://mlsanity.com/paper/2201.02409/) (2022)
- [Localization of Synthetic Manipulations in Western Blot Images](https://mlsanity.com/paper/2408.13786/) (2024)
- [TACTIC: Joint Rate-Distortion-Accuracy Optimisation for Low Bitrate Compression](https://mlsanity.com/paper/2109.10658/) (2021)
- [Transferable Class-Modelling for Decentralized Source Attribution of GAN-Generated Images](https://mlsanity.com/paper/2203.09777/) (2022)
- [Improving Model's Focus Improves Performance of Deep Learning-Based Synthetic Face Detectors](https://mlsanity.com/paper/2303.00818/) (2023)
- [Training Better Deep Learning Models Using Human Saliency](https://mlsanity.com/paper/2410.16190/) (2024)
- [MVFNet: Multipurpose Video Forensics Network using Multiple Forms of Forensic Evidence](https://mlsanity.com/paper/2503.20991/) (2025)
- [Toward Storage-Aware Learning with Compressed Data An Empirical Exploratory Study on JPEG](https://mlsanity.com/paper/2508.12833/) (2025)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have proved very accurate in multiple computer vision image classification tasks that required visual inspection in the past (e.g., object recognition, face detection, etc.). Motivated by these astonishing results, researchers have also started using CNNs to cope with image forensic problems (e.g., camera model identification, tampering detection, etc.). However, in computer vision, image classification methods typically rely on visual cues easily detectable by human eyes. Conversely, forensic solutions rely on almost invisible traces that are often very subtle and lie in the fine details of the image under analysis. For this reason, training a CNN to solve a forensic task requires some special care, as common processing operations (e.g., resampling, compression, etc.) can strongly hinder forensic traces. In this work, we focus on the effect that JPEG has on CNN training considering different computer vision and forensic image classification problems. Specifically, we consider the issues that rise from JPEG compression and misalignment of the JPEG grid. We show that it is necessary to consider these effects when generating a training dataset in order to properly train a forensic detector not losing generalization capability, whereas it is almost possible to ignore these effects for computer vision tasks.