# Local Aggregation for Unsupervised Learning of Visual Embeddings

arXiv: https://arxiv.org/abs/1903.12355 · HTML: https://mlsanity.com/paper/1903.12355/

## Key facts

- Cited by 204 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2019.

## Built on by (most cited first, 30 of 204)

- [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)
- [A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning](https://mlsanity.com/paper/2104.14558/) (2021)
- [DetCo: Unsupervised Contrastive Learning for Object Detection](https://mlsanity.com/paper/2102.04803/) (2021)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering](https://mlsanity.com/paper/2103.17070/) (2021)
- [On Feature Decorrelation in Self-Supervised Learning](https://mlsanity.com/paper/2105.00470/) (2021)
- [RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank](https://mlsanity.com/paper/2210.02885/) (2022)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [Efficient Self-supervised Vision Transformers for Representation Learning](https://mlsanity.com/paper/2106.09785/) (2021)
- [Decoupled Contrastive Learning](https://mlsanity.com/paper/2110.06848/) (2021)
- [Self-supervised Learning in Remote Sensing: A Review](https://mlsanity.com/paper/2206.13188/) (2022)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [Multimodal Contrastive Training for Visual Representation Learning](https://mlsanity.com/paper/2104.12836/) (2021)
- [Neighborhood Contrastive Learning for Novel Class Discovery](https://mlsanity.com/paper/2106.10731/) (2021)
- [What to Hide from Your Students: Attention-Guided Masked Image Modeling](https://mlsanity.com/paper/2203.12719/) (2022)
- [Towards artificial general intelligence via a multimodal foundation model](https://mlsanity.com/paper/2110.14378/) (2021)
- [Contrastive Learning for Many-to-many Multilingual Neural Machine Translation](https://mlsanity.com/paper/2105.09501/) (2021)
- [Efficient Training of Visual Transformers with Small Datasets](https://mlsanity.com/paper/2106.03746/) (2021)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Contrastive Learning with Stronger Augmentations](https://mlsanity.com/paper/2104.07713/) (2021)
- [Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations](https://mlsanity.com/paper/2103.06342/) (2021)
- [Interventional Video Grounding with Dual Contrastive Learning](https://mlsanity.com/paper/2106.11013/) (2021)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery](https://mlsanity.com/paper/2212.05590/) (2022)

## Abstract (arXiv)

Unsupervised approaches to learning in neural networks are of substantial interest for furthering artificial intelligence, both because they would enable the training of networks without the need for large numbers of expensive annotations, and because they would be better models of the kind of general-purpose learning deployed by humans. However, unsupervised networks have long lagged behind the performance of their supervised counterparts, especially in the domain of large-scale visual recognition. Recent developments in training deep convolutional embeddings to maximize non-parametric instance separation and clustering objectives have shown promise in closing this gap. Here, we describe a method that trains an embedding function to maximize a metric of local aggregation, causing similar data instances to move together in the embedding space, while allowing dissimilar instances to separate. This aggregation metric is dynamic, allowing soft clusters of different scales to emerge. We evaluate our procedure on several large-scale visual recognition datasets, achieving state-of-the-art unsupervised transfer learning performance on object recognition in ImageNet, scene recognition in Places 205, and object detection in PASCAL VOC.