mlsanityData to 14 Oct 2026

Geo-DefakeHop: High-Performance Geographic Fake Image Detection

arXiv 2110.09795 ↗First posted 19 Oct 2021cs.CV cs.LG eess.IVcited by 9

Not on the map. Why?

Abstract (arXiv)

A robust fake satellite image detection method, called Geo-DefakeHop, is proposed in this work. Geo-DefakeHop is developed based on the parallel subspace learning (PSL) methodology. PSL maps the input image space into several feature subspaces using multiple filter banks. By exploring response differences of different channels between real and fake images for a filter bank, Geo-DefakeHop learns the most discriminant channels and uses their soft decision scores as features. Then, Geo-DefakeHop selects a few discriminant features from each filter bank and ensemble them to make a final binary decision. Geo-DefakeHop offers a light-weight high-performance solution to fake satellite images detection. Its model size is analyzed, which ranges from 0.8 to 62K parameters. Furthermore, it is shown by experimental results that it achieves an F1-score higher than 95% under various common image manipulations such as resizing, compression and noise corruption.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 19 Oct 2021.

Builds on

21 of 32 references.

References · 21

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  5. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  6. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  7. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
  8. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 575
  9. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  10. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  11. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 254
  12. 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 209
9 more
  1. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  2. 2018FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Facescited by 119
  3. 2021Face Forensics in the Wildcited by 87
  4. 2020DeepFake Detection by Analyzing Convolutional Tracescited by 81
  5. 2018Interpretable Convolutional Neural Networks via Feedforward Designcited by 49
  6. 2019PointHop: An Explainable Machine Learning Method for Point Cloud Classificationcited by 46
  7. 2020CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysiscited by 42
  8. 2021DefakeHop: A Light-Weight High-Performance Deepfake Detectorcited by 31
  9. 2021VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRIcited by 18

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 1; 2024: 1; 2025: 2.

9 papers.

  1. 2022Green Learning: Introduction, Examples and Outlookcited by 30
  2. 2022DefakeHop++: An Enhanced Lightweight Deepfake Detectorcited by 5
  3. 2022PAGER: Progressive Attribute-Guided Extendable Robust Image Generationcited by 5
  4. 2022An Overview on the Generation and Detection of Synthetic and Manipulated Satellite Imagescited by 3
  5. 2024GreenCOD: A Green Camouflaged Object Detection Methodcited by 2
  6. 2025RSFAKE-1M: A Large-Scale Dataset for Detecting Diffusion-Generated Remote Sensing Forgeriescited by 2
  7. 2022Evaluation of Pre-Trained CNN Models for Geographic Fake Image Detectioncited by 1
  8. 2023A One-Class Classifier for the Detection of GAN Manipulated Multi-Spectral Satellite Imagescited by 1
  9. 2025SFNet: Fusion of Spatial and Frequency-Domain Features for Remote Sensing Image Forgery Detectioncited by 1