mlsanityData to 13 Oct 2026

Results and findings of the 2021 Image Similarity Challenge

arXiv 2202.04007 ↗First posted 8 Feb 2022cs.CV cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent image copy detection methods. There were 200 participants to the competition. This paper presents a quantitative and qualitative analysis of the top submissions. It appears that the most difficult image transformations involve either severe image crops or hiding into unrelated images, combined with local pixel perturbations. The key algorithmic elements in the winning submissions are: training on strong augmentations, self-supervised learning, score normalization, explicit overlay detection, and global descriptor matching followed by pairwise image comparison.

Key facts. Cited by 10 papers in the map (data through 13 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 8 Feb 2022.

Builds on

22 of 28 references.

References · 22

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,915
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,730
  6. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,841
  7. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,826
  8. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 498
  9. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 299
  10. 2019Fixing the train-test resolution discrepancycited by 209
  11. 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
  12. 2019Cross-Batch Memory for Embedding Learningcited by 131
10 more
  1. 2020The DeepFake Detection Challenge (DFDC) Datasetcited by 129
  2. 2021The 2021 Image Similarity Dataset and Challengecited by 44
  3. 2022AugLy: Data Augmentations for Robustnesscited by 34
  4. 2021Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detectioncited by 23
  5. 2020Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyondcited by 15
  6. 2021Bag of Tricks and A Strong baseline for Image Copy Detectioncited by 14
  7. 2021D2LV: A Data-Driven and Local-Verification Approach for Image Copy Detectioncited by 7
  8. 2021Producing augmentation-invariant embeddings from real-life imagerycited by 6
  9. 20213rd Place: A Global and Local Dual Retrieval Solution to Facebook AI Image Similarity Challengecited by 4
  10. 20212nd Place Solution to Facebook AI Image Similarity Challenge Matching Trackcited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 4; 2025: 1; 2026: 1.

10 papers.

  1. 2024VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Modelscited by 126
  2. 2022TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervisioncited by 15
  3. 2024TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generationcited by 9
  4. 2022Active Image Indexingcited by 8
  5. 2024AnyPattern: Towards In-context Image Copy Detectioncited by 5
  6. 2024Image Copy Detection for Diffusion Modelscited by 4
  7. 2022General Image Descriptors for Open World Image Retrieval using ViT CLIPcited by 2
  8. 20233rd Place Solution to Meta AI Video Similarity Challengecited by 2
  9. 2025Origin Identification for Text-Guided Image-to-Image Diffusion Modelscited by 1
  10. 2026Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detectioncited by 0