# Mining on Manifolds: Metric Learning without Labels

arXiv: https://arxiv.org/abs/1803.11095 · HTML: https://mlsanity.com/paper/1803.11095/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2018.

## Built on by (most cited first, 30 of 36)

- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo](https://mlsanity.com/paper/2203.17248/) (2022)
- [Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data](https://mlsanity.com/paper/2303.13664/) (2023)
- [Unicom: Universal and Compact Representation Learning for Image Retrieval](https://mlsanity.com/paper/2304.05884/) (2023)
- [Max-Margin Contrastive Learning](https://mlsanity.com/paper/2112.11450/) (2021)
- [Integrating Language Guidance into Vision-based Deep Metric Learning](https://mlsanity.com/paper/2203.08543/) (2022)
- [Contrastive Multi-view Hyperbolic Hierarchical Clustering](https://mlsanity.com/paper/2205.02618/) (2022)
- [Knowledge Evolution in Neural Networks](https://mlsanity.com/paper/2103.05152/) (2021)
- [Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning](https://mlsanity.com/paper/2309.13439/) (2023)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [Self-Taught Metric Learning without Labels](https://mlsanity.com/paper/2205.01903/) (2022)
- [InsCLR: Improving Instance Retrieval with Self-Supervision](https://mlsanity.com/paper/2112.01390/) (2021)
- [On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2208.05744/) (2022)
- [TLDR: Twin Learning for Dimensionality Reduction](https://mlsanity.com/paper/2110.09455/) (2021)
- [Contrastive Bayesian Analysis for Deep Metric Learning](https://mlsanity.com/paper/2210.04402/) (2022)
- [DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning](https://mlsanity.com/paper/2309.11782/) (2023)
- [Improving Deep Metric Learning by Divide and Conquer](https://mlsanity.com/paper/2109.04003/) (2021)
- [Global Contrastive Batch Sampling via Optimization on Sample Permutations](https://mlsanity.com/paper/2210.12874/) (2022)
- [SynCo: Synthetic Hard Negatives for Contrastive Visual Representation Learning](https://mlsanity.com/paper/2410.02401/) (2024)
- [Improving memory banks for unsupervised learning with large mini-batch, consistency and hard negative mining](https://mlsanity.com/paper/2102.04442/) (2021)
- [Exploring Instance Relations for Unsupervised Feature Embedding](https://mlsanity.com/paper/2105.03341/) (2021)
- [Deep Metric Learning for the Hemodynamics Inference with Electrocardiogram Signals](https://mlsanity.com/paper/2308.04650/) (2023)
- [Piecewise-Linear Manifolds for Deep Metric Learning](https://mlsanity.com/paper/2403.14977/) (2024)
- [ROGPL: Robust Open-Set Graph Learning via Region-Based Prototype Learning](https://mlsanity.com/paper/2402.18495/) (2024)
- [Pose-GuideNet: Automatic Scanning Guidance for Fetal Head Ultrasound from Pose Estimation](https://mlsanity.com/paper/2408.09931/) (2024)
- [DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold](https://mlsanity.com/paper/2112.07082/) (2021)
- [Instance Image Retrieval by Learning Purely From Within the Dataset](https://mlsanity.com/paper/2208.06119/) (2022)
- [Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning](https://mlsanity.com/paper/2304.12448/) (2023)
- [A survey of manifold learning and its applications for multimedia](https://mlsanity.com/paper/2310.12986/) (2023)
- [Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairing](https://mlsanity.com/paper/2401.05730/) (2024)

## 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.