mlsanityData to 7 Oct 2026

Noise-resistant Deep Metric Learning with Ranking-based Instance Selection

arXiv 2103.16047 ↗First posted 30 Mar 2021cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains open. In this paper, we propose a noise-resistant training technique for DML, which we name Probabilistic Ranking-based Instance Selection with Memory (PRISM). PRISM identifies noisy data in a minibatch using average similarity against image features extracted by several previous versions of the neural network. These features are stored in and retrieved from a memory bank. To alleviate the high computational cost brought by the memory bank, we introduce an acceleration method that replaces individual data points with the class centers. In extensive comparisons with 12 existing approaches under both synthetic and real-world label noise, PRISM demonstrates superior performance of up to 6.06% in Precision@1.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 42 of its 59 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

42 of 59 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  5. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  6. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  7. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  8. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  9. 2019End-to-End Learning of Visual Representations from Uncurated Instructional Videoscited by 506
  10. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  11. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  12. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
30 more
  1. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  2. 2020A Metric Learning Reality Checkcited by 317
  3. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
  4. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  5. 2017Sampling Matters in Deep Embedding Learningcited by 285
  6. 2017No Fuss Distance Metric Learning using Proxiescited by 225
  7. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  8. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  9. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 184
  10. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  11. 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
  12. 2018Learning to Learn from Noisy Labeled Datacited by 160
  13. 2019Cross-Batch Memory for Embedding Learningcited by 130
  14. 2016End-to-end Learning of Deep Visual Representations for Image Retrievalcited by 122
  15. 2015Learning with Symmetric Label Noise: The Importance of Being Unhingedcited by 120
  16. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  17. 2019Meta Label Correction for Noisy Label Learningcited by 108
  18. 2020ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysiscited by 107
  19. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  20. 2020Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrievalcited by 98
  21. 2017Smart Mining for Deep Metric Learningcited by 96
  22. 2019Ranked List Loss for Deep Metric Learningcited by 77
  23. 2020PyTorch Metric Learningcited by 57
  24. 2020Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxiescited by 36
  25. 2017Distance-based Confidence Score for Neural Network Classifierscited by 30
  26. 2019Distance-Based Learning from Errors for Confidence Calibrationcited by 23
  27. 2020Meta Soft Label Generation for Noisy Labelscited by 21
  28. 2019The Group Loss for Deep Metric Learningcited by 20
  29. 2019Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Datasetcited by 17
  30. 2018Deep Metric Learning by Online Soft Mining and Class-Aware Attentioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 6; 2024: 4; 2025: 3; 2026: 1.

23 papers.

Sort:

By area:

  1. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  2. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  3. 2024Towards Graph Contrastive Learning: A Survey and Beyondcited by 26
  4. 2025Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Datacited by 12
  5. 2021Learning with Label Noise for Image Retrieval by Selecting Interactionscited by 8
  6. 2022RankDNN: Learning to Rank for Few-shot Learningcited by 7
  7. 2022A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculturecited by 6
  8. 2023Center Contrastive Loss for Metric Learningcited by 4
  9. 2022Deep Metric Learning with Chance Constraintscited by 3
  10. 2023A Survey of Historical Learning: Learning Models with Learning Historycited by 3
  11. 2022Deep Image Retrieval is not Robust to Label Noisecited by 2
  12. 2023ProcSim: Proxy-based Confidence for Robust Similarity Learningcited by 2
11 more
  1. 2024Towards certifiable AI in aviation: landscape, challenges, and opportunitiescited by 2
  2. 2025Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalizationcited by 2
  3. 2023Robust Calibrate Proxy Loss for Deep Metric Learningcited by 1
  4. 2023Generalized Sum Pooling for Metric Learningcited by 1
  5. 2023Transformer-empowered Multi-modal Item Embedding for Enhanced Image Search in E-Commercecited by 1
  6. 2024Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detectioncited by 1
  7. 2025Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selectioncited by 1
  8. 2021Noise-Resistant Deep Metric Learning with Probabilistic Instance Filteringcited by 0
  9. 2021LIGAR: Lightweight General-purpose Action Recognitioncited by 0
  10. 2024Debiased Orthogonal Boundary-Driven Efficient Noise Mitigationcited by 0
  11. 2026SynMulti: Synthetic-to-Real Learning for Multimodal Video Understandingcited by 0