mlsanityData to 14 Oct 2026

Learning with Label Noise for Image Retrieval by Selecting Interactions

arXiv 2112.10453 ↗First posted 20 Dec 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Learning with noisy labels is an active research area for image classification. However, the effect of noisy labels on image retrieval has been less studied. In this work, we propose a noise-resistant method for image retrieval named Teacher-based Selection of Interactions, T-SINT, which identifies noisy interactions, ie. elements in the distance matrix, and selects correct positive and negative interactions to be considered in the retrieval loss by using a teacher-based training setup which contributes to the stability. As a result, it consistently outperforms state-of-the-art methods on high noise rates across benchmark datasets with synthetic noise and more realistic noise.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 20 Dec 2021.

Builds on

35 of 47 references.

References · 35

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  8. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  9. 2017A Closer Look at Memorization in Deep Networkscited by 942
  10. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  11. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  12. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
23 more
  1. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  2. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  3. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  4. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  5. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  6. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  7. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  8. 2020A Metric Learning Reality Checkcited by 321
  9. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  10. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  11. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 191
  12. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  13. 2017Learning from Noisy Labels with Distillationcited by 161
  14. 2018Learning to Learn from Noisy Labeled Datacited by 160
  15. 2021SEED: Self-supervised Distillation For Visual Representationcited by 134
  16. 2019Cross-Batch Memory for Embedding Learningcited by 132
  17. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  18. 2016End-to-end Learning of Deep Visual Representations for Image Retrievalcited by 122
  19. 2017Learning From Noisy Large-Scale Datasets With Minimal Supervisioncited by 115
  20. 2020Self-Distillation as Instance-Specific Label Smoothingcited by 71
  21. 2019On Symmetric Losses for Learning from Corrupted Labelscited by 53
  22. 2021Noise-resistant Deep Metric Learning with Ranking-based Instance Selectioncited by 23
  23. 2020S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learningcited by 14

Built on by

Cited by year (2026 to 14 Oct)

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

8 papers.

  1. 2023Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representationscited by 28
  2. 2025Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Datacited by 12
  3. 2022A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculturecited by 6
  4. 2022Deep Image Retrieval is not Robust to Label Noisecited by 2
  5. 2023ProcSim: Proxy-based Confidence for Robust Similarity Learningcited by 2
  6. 2023Transformer-empowered Multi-modal Item Embedding for Enhanced Image Search in E-Commercecited by 1
  7. 2024Debiased Orthogonal Boundary-Driven Efficient Noise Mitigationcited by 0
  8. 2026SynMulti: Synthetic-to-Real Learning for Multimodal Video Understandingcited by 0