mlsanityData to 7 Oct 2026

Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection

arXiv 2409.08884 ↗First posted 13 Sep 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Are general-purpose visual representations acquired solely from synthetic data useful for detecting fake images? In this work, we show the effectiveness of synthetic data-driven representations for synthetic image detection. Upon analysis, we find that vision transformers trained by the latest visual representation learners with synthetic data can effectively distinguish fake from real images without seeing any real images during pre-training. Notably, using SynCLR as the backbone in a state-of-the-art detection method demonstrates a performance improvement of +10.32 mAP and +4.73% accuracy over the widely used CLIP, when tested on previously unseen GAN models. Code is available at https://github.com/cvpaperchallenge/detect-fake-with-fake.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 66 of its 81 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

66 of 81 references.

References · 66

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  10. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  11. 2017Neural Discrete Representation Learningcited by 4,650
  12. 2021Zero-Shot Text-to-Image Generationcited by 4,276
38 more
  1. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  2. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  8. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  9. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  10. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  11. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  12. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  13. 2023Vision Transformers Need Registerscited by 844
  14. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  15. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  16. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  17. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  18. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
  19. 2018Learning to See in the Darkcited by 459
  20. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  21. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 319
  22. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  23. 2021SimSwap: An Efficient Framework For High Fidelity Face Swappingcited by 243
  24. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  25. 2019FaceShifter: Towards High Fidelity And Occlusion Aware Face Swappingcited by 221
  26. 2018Do GANs leave artificial fingerprints?cited by 188
  27. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
  28. 2023StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learnerscited by 177
  29. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  30. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
  31. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  32. 2023Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detectioncited by 126
  33. 20234M: Massively Multimodal Masked Modelingcited by 118
  34. 2023Scaling Laws of Synthetic Images for Model Training ... for Nowcited by 107
  35. 2018ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detectioncited by 104
  36. 2021Pre-training without Natural Imagescited by 100
  37. 2021Learning to See by Looking at Noisecited by 92
  38. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 88

50 most cited of 66 All 66 (JSON)

Built on by

Not cited yet.