# Unsupervised Learning of Dense Visual Representations

Source: [Unsupervised Learning of Dense Visual Representations](<https://www.sota2.com/research/paper/68fa68e21e209131cea1ef6d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:48:52.480Z

Authors: Pedro O. Pinheiro, Amjad Almahairi, Ryan Y. Benmalek, Florian Golemo, Aaron Courville

Published: 2020-11-11T01:28:11.000Z

## Abstract

Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e., compositions of data augmentation) of the same image. However, many visual understanding tasks require dense (pixel-level) representations. In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. VADeR learns pixelwise representations by forcing local features to remain constant over different viewing conditions. Specifically, this is achieved through pixel-level contrastive learning: matching features (that is, features that describes the same location of the scene on different views) should be close in an embedding space, while non-matching features should be apart. VADeR provides a natural representation for dense prediction tasks and transfers well to downstream tasks. Our method outperforms ImageNet supervised pretraining (and strong unsupervised baselines) in multiple dense prediction tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Lung Segmentation on PadChest (five-fold cross-validation)](<https://www.sota2.com/research/sota/lung-segmentation-on-padchest-five-fold-cross-validation.md>): Lung Segmentation; PadChest (five-fold cross-validation); DSC (%): 92.26.

- [Keypoint Detection on MS-COCO 2017 (val)](<https://www.sota2.com/research/sota/keypoint-detection-on-ms-coco-2017-val.md>): Keypoint Detection; MS-COCO 2017 (val); AP: 66.1.

- [Object Detection on COCO (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-val.md>): Object Detection; COCO (val); mAP: 39.2.

- [Instance Segmentation on COCO (val)](<https://www.sota2.com/research/sota/instance-segmentation-on-coco-val.md>): Instance Segmentation; COCO (val); APmk: 35.6.

- [Instance Segmentation on COCO 2017 (val)](<https://www.sota2.com/research/sota/instance-segmentation-on-coco-2017-val.md>): Instance Segmentation; COCO 2017 (val); APm: 0.356.

- [Object Detection on COCO 2017 (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-2017-val.md>): Object Detection; COCO 2017 (val); AP: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2011.05499>)

[PDF](<https://arxiv.org/pdf/2011.05499.pdf>)