mlsanityData to 7 Oct 2026

Mining on Manifolds: Metric Learning without Labels

arXiv 1803.11095 ↗First posted 29 Mar 2018cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

In this work we present a novel unsupervised framework for hard training example mining. The only input to the method is a collection of images relevant to the target application and a meaningful initial representation, provided e.g. by pre-trained CNN. Positive examples are distant points on a single manifold, while negative examples are nearby points on different manifolds. Both types of examples are revealed by disagreements between Euclidean and manifold similarities. The discovered examples can be used in training with any discriminative loss. The method is applied to unsupervised fine-tuning of pre-trained networks for fine-grained classification and particular object retrieval. Our models are on par or are outperforming prior models that are fully or partially supervised.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 8; 2023: 7; 2024: 9; 2025: 1.

36 papers.

Sort:

  1. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  2. 2022Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCocited by 52
  3. 2023Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Datacited by 44
  4. 2023Unicom: Universal and Compact Representation Learning for Image Retrievalcited by 36
  5. 2021Max-Margin Contrastive Learningcited by 27
  6. 2022Integrating Language Guidance into Vision-based Deep Metric Learningcited by 19
  7. 2022Contrastive Multi-view Hyperbolic Hierarchical Clusteringcited by 19
  8. 2021Knowledge Evolution in Neural Networkscited by 18
  9. 2023Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learningcited by 18
  10. 2024Does Negative Sampling Matter? A Review with Insights into its Theory and Applicationscited by 14
  11. 2022Self-Taught Metric Learning without Labelscited by 13
  12. 2021InsCLR: Improving Instance Retrieval with Self-Supervisioncited by 11
24 more
  1. 2022On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learningcited by 10
  2. 2021TLDR: Twin Learning for Dimensionality Reductioncited by 9
  3. 2022Contrastive Bayesian Analysis for Deep Metric Learningcited by 8
  4. 2021Improving Deep Metric Learning by Divide and Conquercited by 5
  5. 2022Global Contrastive Batch Sampling via Optimization on Sample Permutationscited by 5
  6. 2024SynCo: Synthetic Hard Negatives for Contrastive Visual Representation Learningcited by 5
  7. 2021Improving memory banks for unsupervised learning with large mini-batch, consistency and hard negative miningcited by 4
  8. 2021Exploring Instance Relations for Unsupervised Feature Embeddingcited by 4
  9. 2023Deep Metric Learning for the Hemodynamics Inference with Electrocardiogram Signalscited by 4
  10. 2023DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learningcited by 4
  11. 2024Piecewise-Linear Manifolds for Deep Metric Learningcited by 4
  12. 2024ROGPL: Robust Open-Set Graph Learning via Region-Based Prototype Learningcited by 2
  13. 2024Pose-GuideNet: Automatic Scanning Guidance for Fetal Head Ultrasound from Pose Estimationcited by 2
  14. 2021DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifoldcited by 1
  15. 2022Instance Image Retrieval by Learning Purely From Within the Datasetcited by 1
  16. 2023Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learningcited by 1
  17. 2023A survey of manifold learning and its applications for multimediacited by 1
  18. 2024Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenescited by 1
  19. 2025Unsupervised Ground Metric Learningcited by 1
  20. 2021Unsupervised Embedding Learning from Uncertainty Momentum Modelingcited by 0
  21. 2021Towards noise robust trigger-word detection with contrastive learning pre-task for fast on-boarding of new trigger-wordscited by 0
  22. 2024Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairingcited by 0
  23. 2024GLRT-Based Metric Learning for Remote Sensing Object Retrievalcited by 0
  24. 2024Retrieval Augmented Image Harmonizationcited by 0