mlsanityData to 7 Oct 2026

A Self-Supervised Descriptor for Image Copy Detection

arXiv 2202.10261 ↗First posted 21 Feb 2022cs.CV cs.CR cs.LGcited by 175

Not on the map. Why?

Cited by 94 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image copy detection is an important task for content moderation. We introduce SSCD, a model that builds on a recent self-supervised contrastive training objective. We adapt this method to the copy detection task by changing the architecture and training objective, including a pooling operator from the instance matching literature, and adapting contrastive learning to augmentations that combine images. Our approach relies on an entropy regularization term, promoting consistent separation between descriptor vectors, and we demonstrate that this significantly improves copy detection accuracy. Our method produces a compact descriptor vector, suitable for real-world web scale applications. Statistical information from a background image distribution can be incorporated into the descriptor. On the recent DISC2021 benchmark, SSCD is shown to outperform both baseline copy detection models and self-supervised architectures designed for image classification by huge margins, in all settings. For example, SSCD out-performs SimCLR descriptors by 48% absolute. Code is available at https://github.com/facebookresearch/sscd-copy-detection.

Key facts. Cited by 175 papers in the map (data through 7 Oct 2026). Builds on 36 of its 63 references that are in the map. First posted on arXiv 21 Feb 2022.

Builds on

36 of 63 references.

References · 36

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  10. 2017Billion-scale similarity search with GPUscited by 2,477
  11. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  12. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
24 more
  1. 2017Large Batch Training of Convolutional Networkscited by 529
  2. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  3. 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 485
  4. 2017Word Translation Without Parallel Datacited by 480
  5. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
  6. 2021Understanding Dimensional Collapse in Contrastive Self-supervised Learningcited by 374
  7. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  8. 2015YFCC100M: The New Data in Multimedia Researchcited by 234
  9. 2019Fixing the train-test resolution discrepancycited by 209
  10. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  11. 2015Particular object retrieval with integral max-pooling of CNN activationscited by 160
  12. 2018Learning Rich Features for Image Manipulation Detectioncited by 154
  13. 2016Deep Image Retrieval: Learning global representations for image searchcited by 147
  14. 2018Spreading vectors for similarity searchcited by 114
  15. 2021Training Vision Transformers for Image Retrievalcited by 90
  16. 2020Distortion Agnostic Deep Watermarkingcited by 88
  17. 2019MultiGrain: a unified image embedding for classes and instancescited by 85
  18. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  19. 2020Learning and aggregating deep local descriptors for instance-level recognitioncited by 54
  20. 2021The 2021 Image Similarity Dataset and Challengecited by 44
  21. 2014Multi-scale Orderless Pooling of Deep Convolutional Activation Featurescited by 38
  22. 2018Trends in the Diffusion of Misinformation on Social Mediacited by 25
  23. 2018Image Provenance Analysis at Scalecited by 16
  24. 2021OSCAR-Net: Object-centric Scene Graph Attention for Image Attributioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 25; 2024: 54; 2025: 49; 2026: 43.

175 papers.

Sort:

By area:

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  3. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  4. 2024The Faiss librarycited by 370
  5. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 312
  6. 2023A Cookbook of Self-Supervised Learningcited by 248
  7. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  8. 2023Understanding and Mitigating Copying in Diffusion Modelscited by 205
  9. 2023One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applicationscited by 164
  10. 2025HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformercited by 131
  11. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Samplingcited by 124
  12. 2024Measuring Style Similarity in Diffusion Modelscited by 106
38 more
  1. 2024Detecting, Explaining, and Mitigating Memorization in Diffusion Modelscited by 94
  2. 2024GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Controlcited by 76
  3. 2024Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attentioncited by 57
  4. 2024Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributionscited by 53
  5. 2025FineVision: Open Data Is All You Needcited by 51
  6. 2024Towards Memorization-Free Diffusion Modelscited by 49
  7. 2024Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approachcited by 48
  8. 2023On the De-duplication of LAION-2Bcited by 47
  9. 2023Evaluating Data Attribution for Text-to-Image Modelscited by 45
  10. 2024Towards a Mechanistic Explanation of Diffusion Model Generalizationcited by 42
  11. 2022Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNetcited by 41
  12. 2024A Geometric Framework for Understanding Memorization in Generative Modelscited by 40
  13. 2024Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Modelscited by 36
  14. 2023Real-Fake: Effective Training Data Synthesis Through Distribution Matchingcited by 35
  15. 2024The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipelinecited by 33
  16. 2026FireRed-Image-Edit-1.0 Technical Reportcited by 31
  17. 2026HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformercited by 29
  18. 2024Residual Quantization with Implicit Neural Codebookscited by 24
  19. 2025Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Modelscited by 24
  20. 2025On the Edge of Memorization in Diffusion Modelscited by 22
  21. 2023The Emergence of Reproducibility and Generalizability in Diffusion Modelscited by 21
  22. 2024Classifier-Free Guidance inside the Attraction Basin May Cause Memorizationcited by 21
  23. 2024Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapescited by 20
  24. 2024Exploring Local Memorization in Diffusion Models via Bright Ending Attentioncited by 19
  25. 2023NewMove: Customizing text-to-video models with novel motionscited by 18
  26. 2025Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modelingcited by 18
  27. 2025Data Unlearning in Diffusion Modelscited by 18
  28. 2024ProMark: Proactive Diffusion Watermarking for Causal Attributioncited by 16
  29. 2025Privacy Attacks on Image AutoRegressive Modelscited by 15
  30. 2024Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modelingcited by 13
  31. 2023Self-Supervised Video Similarity Learningcited by 12
  32. 2024VIXEN: Visual Text Comparison Network for Image Difference Captioningcited by 12
  33. 2024Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Modelscited by 12
  34. 2024ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative Generationcited by 12
  35. 2024Unlearning or Concealment? A Critical Analysis and Evaluation Metrics for Unlearning in Diffusion Modelscited by 12
  36. 2025Does Training with Synthetic Data Truly Protect Privacy?cited by 12
  37. 2025Generative Modeling of Weights: Generalization or Memorization?cited by 12
  38. 2025AirSim360: A Panoramic Simulation Platform within Drone Viewcited by 12

50 most cited of 175 All 175 (JSON)