# Pretrained equivariant features improve unsupervised landmark discovery

arXiv: https://arxiv.org/abs/2104.02925 · HTML: https://mlsanity.com/paper/2104.02925/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 20 of 20)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Convolutional neural network architecture for geometric matching](https://mlsanity.com/paper/1703.05593/) (2017)
- [Unsupervised Learning of Object Landmarks through Conditional Image Generation](https://mlsanity.com/paper/1806.07823/) (2018)
- [Learning What and Where to Draw](https://mlsanity.com/paper/1610.02454/) (2016)
- [Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning](https://mlsanity.com/paper/1807.03146/) (2018)
- [Unsupervised Discovery of Object Landmarks as Structural Representations](https://mlsanity.com/paper/1804.04412/) (2018)
- [Numerical Coordinate Regression with Convolutional Neural Networks](https://mlsanity.com/paper/1801.07372/) (2018)
- [Parallel Multiscale Autoregressive Density Estimation](https://mlsanity.com/paper/1703.03664/) (2017)
- [Unsupervised learning of object landmarks by factorized spatial embeddings](https://mlsanity.com/paper/1705.02193/) (2017)
- [Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance](https://mlsanity.com/paper/1806.06503/) (2018)
- [Flowing ConvNets for Human Pose Estimation in Videos](https://mlsanity.com/paper/1506.02897/) (2015)
- [Unsupervised Learning of Landmarks by Descriptor Vector Exchange](https://mlsanity.com/paper/1908.06427/) (2019)
- [Learning Deep Representation for Face Alignment with Auxiliary Attributes](https://mlsanity.com/paper/1408.3967/) (2014)
- [Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations](https://mlsanity.com/paper/1407.3399/) (2014)
- [WarpNet: Weakly Supervised Matching for Single-view Reconstruction](https://mlsanity.com/paper/1604.05592/) (2016)
- [Simultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion](https://mlsanity.com/paper/1709.08130/) (2017)
- [Deep Deformation Network for Object Landmark Localization](https://mlsanity.com/paper/1605.01014/) (2016)
- [Unsupervised learning of object frames by dense equivariant image labelling](https://mlsanity.com/paper/1706.02932/) (2017)
- [Object landmark discovery through unsupervised adaptation](https://mlsanity.com/paper/1910.09469/) (2019)

## Built on by (most cited first, 2 of 2)

- [C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation](https://mlsanity.com/paper/2212.11078/) (2022)
- [Iterative Contrast-Classify For Semi-supervised Temporal Action Segmentation](https://mlsanity.com/paper/2112.01402/) (2021)

## Abstract (arXiv)

Locating semantically meaningful landmark points is a crucial component of a large number of computer vision pipelines. Because of the small number of available datasets with ground truth landmark annotations, it is important to design robust unsupervised and semi-supervised methods for landmark detection. Many of the recent unsupervised learning methods rely on the equivariance properties of landmarks to synthetic image deformations. Our work focuses on such widely used methods and sheds light on its core problem, its inability to produce equivariant intermediate convolutional features. This finding leads us to formulate a two-step unsupervised approach that overcomes this challenge by first learning powerful pixel-based features and then use the pre-trained features to learn a landmark detector by the traditional equivariance method. Our method produces state-of-the-art results in several challenging landmark detection datasets such as the BBC Pose dataset and the Cat-Head dataset. It performs comparably on a range of other benchmarks.