mlsanityData to 13 Oct 2026

[RE] CNN-generated images are surprisingly easy to spot...for now

arXiv 2104.02984 ↗First posted 7 Apr 2021cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

This work evaluates the reproducibility of the paper "CNN-generated images are surprisingly easy to spot... for now" by Wang et al. published at CVPR 2020. The paper addresses the challenge of detecting CNN-generated imagery, which has reached the potential to even fool humans. The authors propose two methods which help an image classifier to generalize from being trained on one specific CNN to detecting imagery produced by unseen architectures, training methods, or data sets. The paper proposes two methods to help a classifier generalize: (i) utilizing different kinds of data augmentations and (ii) using a diverse data set. This report focuses on assessing if these techniques indeed help the generalization process. Furthermore, we perform additional experiments to study the limitations of the proposed techniques.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 29 of its 35 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

29 of 35 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,476
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,000
  7. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,516
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,585
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,975
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,619
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,906
  12. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,549
17 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,296
  3. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,097
  4. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  5. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 846
  6. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  7. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  8. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  9. 2018Learning to See in the Darkcited by 459
  10. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  11. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  12. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  13. 2018Learning Rich Features for Image Manipulation Detectioncited by 154
  14. 2018Fighting Fake News: Image Splice Detection via Learned Self-Consistencycited by 136
  15. 2018Diverse Image Synthesis from Semantic Layouts via Conditional IMLEcited by 60
  16. 2019Detecting Photoshopped Faces by Scripting Photoshopcited by 55
  17. 2019FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Facescited by 12

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Sequential training of GANs against GAN-classifiers reveals correlated "knowledge gaps" present among independently trained GAN instancescited by 1