mlsanityData to 7 Oct 2026

D2LV: A Data-Driven and Local-Verification Approach for Image Copy Detection

arXiv 2111.07090 ↗First posted 13 Nov 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Image copy detection is of great importance in real-life social media. In this paper, a data-driven and local-verification (D2LV) approach is proposed to compete for Image Similarity Challenge: Matching Track at NeurIPS'21. In D2LV, unsupervised pre-training substitutes the commonly-used supervised one. When training, we design a set of basic and six advanced transformations, and a simple but effective baseline learns robust representation. During testing, a global-local and local-global matching strategy is proposed. The strategy performs local-verification between reference and query images. Experiments demonstrate that the proposed method is effective. The proposed approach ranks first out of 1,103 participants on the Facebook AI Image Similarity Challenge: Matching Track. The code and trained models are available at https://github.com/WangWenhao0716/ISC-Track1-Submission.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 24 of its 38 references that are in the map. First posted on arXiv 13 Nov 2021.

Builds on

24 of 38 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  8. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  9. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  10. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  11. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  12. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
12 more
  1. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 472
  2. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  3. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  4. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  5. 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
  6. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  7. 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
  8. 2019MultiGrain: a unified image embedding for classes and instancescited by 85
  9. 2021The 2021 Image Similarity Dataset and Challengecited by 44
  10. 2020VehicleNet: Learning Robust Visual Representation for Vehicle Re-identificationcited by 42
  11. 2020DomainMix: Learning Generalizable Person Re-Identification Without Human Annotationscited by 17
  12. 2021Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learningcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 1; 2025: 0; 2026: 2.

7 papers.

  1. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  2. 2022Results and findings of the 2021 Image Similarity Challengecited by 10
  3. 2022A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detectioncited by 9
  4. 2022V2L: Leveraging Vision and Vision-language Models into Large-scale Product Retrievalcited by 3
  5. 2023Feature-compatible Progressive Learning for Video Copy Detectioncited by 2
  6. 2026Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detectioncited by 0
  7. 2026Agent Safety Should Be a Runtime Contractcited by 0