mlsanityData to 14 Oct 2026

Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detection

arXiv 2112.04323 ↗First posted 8 Dec 2021cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Copy detection, which is a task to determine whether an image is a modified copy of any image in a database, is an unsolved problem. Thus, we addressed copy detection by training convolutional neural networks (CNNs) with contrastive learning. Training with a large memory-bank and hard data augmentation enables the CNNs to obtain more discriminative representation. Our proposed negative embedding subtraction further boosts the copy detection accuracy. Using our methods, we achieved 1st place in the Facebook AI Image Similarity Challenge: Descriptor Track. Our code is publicly available here: urlhttps://github.com/lyakaap/ISC21-Descriptor-Track-1st

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 13 of its 24 references that are in the map. First posted on arXiv 8 Dec 2021.

Builds on

13 of 24 references.

References · 13

  1. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  2. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  4. 2017Billion-scale similarity search with GPUscited by 2,497
  5. 2017Random Erasing Data Augmentationcited by 1,239
  6. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  7. 2014Deep metric learning using Triplet networkcited by 422
  8. 2014Learning Fine-grained Image Similarity with Deep Rankingcited by 190
  9. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 185
  10. 2019Cross-Batch Memory for Embedding Learningcited by 132
  11. 2021The 2021 Image Similarity Dataset and Challengecited by 44
  12. 2020Two-stage Discriminative Re-ranking for Large-scale Landmark Retrievalcited by 18
1 more
  1. 2019Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Datasetcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 7; 2025: 2; 2026: 4.

23 papers.

Sort:

By area:

  1. 2023DataComp: In search of the next generation of multimodal datasetscited by 644
  2. 2022TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervisioncited by 15
  3. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  4. 2022Results and findings of the 2021 Image Similarity Challengecited by 10
  5. 2022A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detectioncited by 9
  6. 2023The 2023 Video Similarity Dataset and Challengecited by 9
  7. 2024TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generationcited by 9
  8. 2022Active Image Indexingcited by 8
  9. 2026WorldVQA: Measuring Atomic World Knowledge in Multimodal Large Language Modelscited by 8
  10. 2024AnyPattern: Towards In-context Image Copy Detectioncited by 5
  11. 2024Self-Supervised Representation Learning for Adversarial Attack Detectioncited by 4
  12. 2024Image Copy Detection for Diffusion Modelscited by 4
11 more
  1. 2025A Survey of LLM × DATAcited by 4
  2. 2026PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Modelscited by 4
  3. 2023Feature-compatible Progressive Learning for Video Copy Detectioncited by 2
  4. 20233rd Place Solution to Meta AI Video Similarity Challengecited by 2
  5. 2024The Effects of Short Video-Sharing Services on Video Copy Detectioncited by 1
  6. 2024Relational Self-supervised Distillation with Compact Descriptors for Image Copy Detectioncited by 1
  7. 2025Origin Identification for Text-Guided Image-to-Image Diffusion Modelscited by 1
  8. 2023Video Infringement Detection via Feature Disentanglement and Mutual Information Maximizationcited by 0
  9. 2023Training CLIP models on Data from Scientific Paperscited by 0
  10. 2026Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detectioncited by 0
  11. 2026HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learningcited by 0