# Unsupervised Deep Learning by Neighbourhood Discovery

arXiv: https://arxiv.org/abs/1904.11567 · HTML: https://mlsanity.com/paper/1904.11567/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2019.

## Built on by (most cited first, 30 of 78)

- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Context Autoencoder for Self-Supervised Representation Learning](https://mlsanity.com/paper/2202.03026/) (2022)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [Selective-Supervised Contrastive Learning with Noisy Labels](https://mlsanity.com/paper/2203.04181/) (2022)
- [Broaden Your Views for Self-Supervised Video Learning](https://mlsanity.com/paper/2103.16559/) (2021)
- [Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision](https://mlsanity.com/paper/2202.08360/) (2022)
- [Mean Shift for Self-Supervised Learning](https://mlsanity.com/paper/2105.07269/) (2021)
- [A Broad Study of Pre-training for Domain Generalization and Adaptation](https://mlsanity.com/paper/2203.11819/) (2022)
- [Self-supervised Video Transformer](https://mlsanity.com/paper/2112.01514/) (2021)
- [Mugs: A Multi-Granular Self-Supervised Learning Framework](https://mlsanity.com/paper/2203.14415/) (2022)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering](https://mlsanity.com/paper/2105.13353/) (2021)
- [Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations](https://mlsanity.com/paper/2106.05967/) (2021)
- [Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.09744/) (2022)
- [Prototypical Graph Contrastive Learning](https://mlsanity.com/paper/2106.09645/) (2021)
- [Geographical Knowledge-driven Representation Learning for Remote Sensing Images](https://mlsanity.com/paper/2107.05276/) (2021)
- [Exploring the Limits of Deep Image Clustering using Pretrained Models](https://mlsanity.com/paper/2303.17896/) (2023)
- [Self-supervised Learning from 100 Million Medical Images](https://mlsanity.com/paper/2201.01283/) (2022)
- [Unsupervised Multi-Source Domain Adaptation for Person Re-Identification](https://mlsanity.com/paper/2104.12961/) (2021)
- [Dense Semantic Contrast for Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2109.07756/) (2021)
- [I Don't Need u: Identifiable Non-Linear ICA Without Side Information](https://mlsanity.com/paper/2106.05238/) (2021)
- [Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks](https://mlsanity.com/paper/2206.03826/) (2022)
- [Discrete Key-Value Bottleneck](https://mlsanity.com/paper/2207.11240/) (2022)
- [Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning](https://mlsanity.com/paper/2101.08732/) (2021)
- [Feature Separation and Recalibration for Adversarial Robustness](https://mlsanity.com/paper/2303.13846/) (2023)
- [Self-Taught Metric Learning without Labels](https://mlsanity.com/paper/2205.01903/) (2022)
- [Deep Clustering by Semantic Contrastive Learning](https://mlsanity.com/paper/2103.02662/) (2021)

## Abstract (arXiv)

Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations. However, training CNNs relies heavily on the availability of exhaustive training data annotations, limiting significantly their deployment and scalability in many application scenarios. In this work, we introduce a generic unsupervised deep learning approach to training deep models without the need for any manual label supervision. Specifically, we progressively discover sample anchored/centred neighbourhoods to reason and learn the underlying class decision boundaries iteratively and accumulatively. Every single neighbourhood is specially formulated so that all the member samples can share the same unseen class labels at high probability for facilitating the extraction of class discriminative feature representations during training. Experiments on image classification show the performance advantages of the proposed method over the state-of-the-art unsupervised learning models on six benchmarks including both coarse-grained and fine-grained object image categorisation.