# Unsupervised Learning of Landmarks by Descriptor Vector Exchange

arXiv: https://arxiv.org/abs/1908.06427 · HTML: https://mlsanity.com/paper/1908.06427/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2019.

## Built on by (most cited first, 30 of 39)

- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Unsupervised Object-Level Representation Learning from Scene Images](https://mlsanity.com/paper/2106.11952/) (2021)
- [Spatially Consistent Representation Learning](https://mlsanity.com/paper/2103.06122/) (2021)
- [KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control](https://mlsanity.com/paper/2104.11224/) (2021)
- [Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation](https://mlsanity.com/paper/2206.12772/) (2022)
- [Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps](https://mlsanity.com/paper/2312.13216/) (2023)
- [ASIC: Aligning Sparse in-the-wild Image Collections](https://mlsanity.com/paper/2303.16201/) (2023)
- [Unsupervised Human Pose Estimation through Transforming Shape Templates](https://mlsanity.com/paper/2105.04154/) (2021)
- [Multi-task head pose estimation in-the-wild](https://mlsanity.com/paper/2202.02299/) (2022)
- [Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency](https://mlsanity.com/paper/2105.06463/) (2021)
- [Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning](https://mlsanity.com/paper/2303.17142/) (2023)
- [Self-Supervised Facial Representation Learning with Facial Region Awareness](https://mlsanity.com/paper/2403.02138/) (2024)
- [Semi-supervised Keypoint Localization](https://mlsanity.com/paper/2101.07988/) (2021)
- [GANORCON: Are Generative Models Useful for Few-shot Segmentation?](https://mlsanity.com/paper/2112.00854/) (2021)
- [HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences](https://mlsanity.com/paper/2103.15573/) (2021)
- [Demystifying Unsupervised Semantic Correspondence Estimation](https://mlsanity.com/paper/2207.05054/) (2022)
- [JOINED : Prior Guided Multi-task Learning for Joint Optic Disc/Cup Segmentation and Fovea Detection](https://mlsanity.com/paper/2203.00461/) (2022)
- [Few-shot Geometry-Aware Keypoint Localization](https://mlsanity.com/paper/2303.17216/) (2023)
- [SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation](https://mlsanity.com/paper/2405.18322/) (2024)
- [Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence](https://mlsanity.com/paper/2506.08220/) (2025)
- [LatentKeypointGAN: Controlling Images via Latent Keypoints](https://mlsanity.com/paper/2103.15812/) (2021)
- [Template NeRF: Towards Modeling Dense Shape Correspondences from Category-Specific Object Images](https://mlsanity.com/paper/2111.04237/) (2021)
- [PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognition](https://mlsanity.com/paper/2309.13822/) (2023)
- [From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery](https://mlsanity.com/paper/2205.15895/) (2022)
- [Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment](https://mlsanity.com/paper/2405.13781/) (2024)
- [LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity](https://mlsanity.com/paper/2204.02958/) (2022)
- [Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors](https://mlsanity.com/paper/2309.16646/) (2023)
- [Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery](https://mlsanity.com/paper/2403.16194/) (2024)
- [Pretrained equivariant features improve unsupervised landmark discovery](https://mlsanity.com/paper/2104.02925/) (2021)
- [Unsupervised 3D Keypoint Discovery with Multi-View Geometry](https://mlsanity.com/paper/2211.12829/) (2022)

## Abstract (arXiv)

Equivariance to random image transformations is an effective method to learn landmarks of object categories, such as the eyes and the nose in faces, without manual supervision. However, this method does not explicitly guarantee that the learned landmarks are consistent with changes between different instances of the same object, such as different facial identities. In this paper, we develop a new perspective on the equivariance approach by noting that dense landmark detectors can be interpreted as local image descriptors equipped with invariance to intra-category variations. We then propose a direct method to enforce such an invariance in the standard equivariant loss. We do so by exchanging descriptor vectors between images of different object instances prior to matching them geometrically. In this manner, the same vectors must work regardless of the specific object identity considered. We use this approach to learn vectors that can simultaneously be interpreted as local descriptors and dense landmarks, combining the advantages of both. Experiments on standard benchmarks show that this approach can match, and in some cases surpass state-of-the-art performance amongst existing methods that learn landmarks without supervision. Code is available at www.robots.ox.ac.uk/~vgg/research/DVE/.