# Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection

arXiv: https://arxiv.org/abs/1804.01552 · HTML: https://mlsanity.com/paper/1804.01552/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2018.

## Built on by (most cited first, 27 of 27)

- [PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering](https://mlsanity.com/paper/2103.17070/) (2021)
- [Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods](https://mlsanity.com/paper/2205.11508/) (2022)
- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation](https://mlsanity.com/paper/2303.04869/) (2023)
- [Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training](https://mlsanity.com/paper/2305.13689/) (2023)
- [Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species](https://mlsanity.com/paper/2112.06183/) (2021)
- [ASIC: Aligning Sparse in-the-wild Image Collections](https://mlsanity.com/paper/2303.16201/) (2023)
- [Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation](https://mlsanity.com/paper/2303.10100/) (2023)
- [Learning Augmentation Distributions using Transformed Risk Minimization](https://mlsanity.com/paper/2111.08190/) (2021)
- [From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detection](https://mlsanity.com/paper/2304.03140/) (2023)
- [Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment](https://mlsanity.com/paper/2211.13264/) (2022)
- [Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization](https://mlsanity.com/paper/2211.15059/) (2022)
- [Learning Geometry-aware Representations by Sketching](https://mlsanity.com/paper/2304.08204/) (2023)
- [Mix-up Self-Supervised Learning for Contrast-agnostic Applications](https://mlsanity.com/paper/2204.00901/) (2022)
- [Representation Learning Dynamics of Self-Supervised Models](https://mlsanity.com/paper/2309.02011/) (2023)
- [Self-Supervised Learning for Text Recognition: A Critical Survey](https://mlsanity.com/paper/2407.19889/) (2024)
- [ProcSim: Proxy-based Confidence for Robust Similarity Learning](https://mlsanity.com/paper/2311.00668/) (2023)
- [PartCo: Part-Level Correspondence Priors Enhance Category Discovery](https://mlsanity.com/paper/2509.22769/) (2025)
- [Curricular and Cyclical Loss for Time Series Learning Strategy](https://mlsanity.com/paper/2312.15853/) (2023)
- [Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data](https://mlsanity.com/paper/2402.17653/) (2024)
- [Spatial Context-based Self-Supervised Learning for Handwritten Text Recognition](https://mlsanity.com/paper/2404.11585/) (2024)
- [Quantum Curriculum Learning](https://mlsanity.com/paper/2407.02419/) (2024)
- [Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels](https://mlsanity.com/paper/2303.18106/) (2023)
- [Learning Spiking Neural Network from Easy to Hard task](https://mlsanity.com/paper/2309.04737/) (2023)
- [Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection](https://mlsanity.com/paper/2507.07994/) (2025)

## Abstract (arXiv)

Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks. While self-supervision has usually been considered for tasks such as image classification, in this paper we aim at extending it to geometry-oriented tasks such as semantic matching and part detection. We do so by building on several recent ideas in unsupervised landmark detection. Our approach learns dense distinctive visual descriptors from an unlabelled dataset of images using synthetic image transformations. It does so by means of a robust probabilistic formulation that can introspectively determine which image regions are likely to result in stable image matching. We show empirically that a network pre-trained in this manner requires significantly less supervision to learn semantic object parts compared to numerous pre-training alternatives. We also show that the pre-trained representation is excellent for semantic object matching.