# Unsupervised Landmark Discovery Using Consistency Guided Bottleneck

arXiv: https://arxiv.org/abs/2309.10518 · HTML: https://mlsanity.com/paper/2309.10518/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 19 Sep 2023.

## Builds on (most cited first, 30 of 31)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [Joint Unsupervised Learning of Deep Representations and Image Clusters](https://mlsanity.com/paper/1604.03628/) (2016)
- [Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression](https://mlsanity.com/paper/1904.07399/) (2019)
- [Unsupervised Learning of Object Landmarks through Conditional Image Generation](https://mlsanity.com/paper/1806.07823/) (2018)
- [Boosting Self-Supervised Learning via Knowledge Transfer](https://mlsanity.com/paper/1805.00385/) (2018)
- [LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood](https://mlsanity.com/paper/2004.02980/) (2020)
- [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)
- [Unsupervised Part-Based Disentangling of Object Shape and Appearance](https://mlsanity.com/paper/1903.06946/) (2019)
- [Unsupervised learning of object landmarks by factorized spatial embeddings](https://mlsanity.com/paper/1705.02193/) (2017)
- [Style Aggregated Network for Facial Landmark Detection](https://mlsanity.com/paper/1803.04108/) (2018)
- [Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance](https://mlsanity.com/paper/1806.06503/) (2018)
- [Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images](https://mlsanity.com/paper/1612.06341/) (2016)
- [Self-supervised learning of a facial attribute embedding from video](https://mlsanity.com/paper/1808.06882/) (2018)
- [Learning to Cluster Faces via Confidence and Connectivity Estimation](https://mlsanity.com/paper/2004.00445/) (2020)
- [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)
- [AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces](https://mlsanity.com/paper/1909.04951/) (2019)
- [Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion](https://mlsanity.com/paper/1904.11960/) (2019)
- [Object landmark discovery through unsupervised adaptation](https://mlsanity.com/paper/1910.09469/) (2019)
- [Unsupervised Landmark Learning from Unpaired Data](https://mlsanity.com/paper/2007.01053/) (2020)

## Built on by (most cited first, 1 of 1)

- [Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery](https://mlsanity.com/paper/2403.16194/) (2024)

## Abstract (arXiv)

We study a challenging problem of unsupervised discovery of object landmarks. Many recent methods rely on bottlenecks to generate 2D Gaussian heatmaps however, these are limited in generating informed heatmaps while training, presumably due to the lack of effective structural cues. Also, it is assumed that all predicted landmarks are semantically relevant despite having no ground truth supervision. In the current work, we introduce a consistency-guided bottleneck in an image reconstruction-based pipeline that leverages landmark consistency, a measure of compatibility score with the pseudo-ground truth to generate adaptive heatmaps. We propose obtaining pseudo-supervision via forming landmark correspondence across images. The consistency then modulates the uncertainty of the discovered landmarks in the generation of adaptive heatmaps which rank consistent landmarks above their noisy counterparts, providing effective structural information for improved robustness. Evaluations on five diverse datasets including MAFL, AFLW, LS3D, Cats, and Shoes demonstrate excellent performance of the proposed approach compared to the existing state-of-the-art methods. Our code is publicly available at https://github.com/MamonaAwan/CGB_ULD.