mlsanityData to 14 Oct 2026

Representation Uncertainty in Self-Supervised Learning as Variational Inference

arXiv 2203.11437 ↗First posted 22 Mar 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

In this study, a novel self-supervised learning (SSL) method is proposed, which considers SSL in terms of variational inference to learn not only representation but also representation uncertainties. SSL is a method of learning representations without labels by maximizing the similarity between image representations of different augmented views of an image. Meanwhile, variational autoencoder (VAE) is an unsupervised representation learning method that trains a probabilistic generative model with variational inference. Both VAE and SSL can learn representations without labels, but their relationship has not been investigated in the past. Herein, the theoretical relationship between SSL and variational inference has been clarified. Furthermore, a novel method, namely variational inference SimSiam (VI-SimSiam), has been proposed. VI-SimSiam can predict the representation uncertainty by interpreting SimSiam with variational inference and defining the latent space distribution. The present experiments qualitatively show that VI- SimSiam could learn uncertainty by comparing input images and predicted uncertainties. Additionally, we described a relationship between estimated uncertainty and classification accuracy.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 42 of its 62 references that are in the map. First posted on arXiv 22 Mar 2022.

Builds on

42 of 62 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  11. 2013Describing Textures in the Wildcited by 2,125
  12. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
30 more
  1. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  2. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  3. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  4. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  5. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  6. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  7. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  8. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  9. 2017Large Batch Training of Convolutional Networkscited by 535
  10. 2021Understanding self-supervised Learning Dynamics without Contrastive Pairscited by 256
  11. 2017VAE with a VampPriorcited by 248
  12. 2018Multimodal Generative Models for Scalable Weakly-Supervised Learningcited by 200
  13. 2018Hyperspherical Variational Auto-Encoderscited by 189
  14. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  15. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  16. 2019Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Modelscited by 178
  17. 2018Bounding Box Regression with Uncertainty for Accurate Object Detectioncited by 143
  18. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  19. 2021Generalized Multimodal ELBOcited by 87
  20. 2020How Useful is Self-Supervised Pretraining for Visual Tasks?cited by 80
  21. 2018Safe Reinforcement Learning with Model Uncertainty Estimatescited by 72
  22. 2018Probabilistic Object Detection: Definition and Evaluationcited by 55
  23. 2021Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Frameworkcited by 49
  24. 2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
  25. 2021Digging into Uncertainty in Self-supervised Multi-view Stereocited by 31
  26. 2020PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inferencecited by 23
  27. 2018Multi-Source Neural Variational Inferencecited by 9
  28. 2021Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurancecited by 8
  29. 2020Uncertainty-aware Self-supervised 3D Data Associationcited by 6
  30. 2019Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictorcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 7; 2025: 6; 2026: 5.

22 papers.

Sort:

By area:

  1. 2022Augmenting Reinforcement Learning with Transformer-based Scene Representation Learning for Decision-making of Autonomous Drivingcited by 24
  2. 2025UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Networkcited by 11
  3. 2024Pretrained Visual Uncertaintiescited by 10
  4. 2025FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detectioncited by 10
  5. 2024Collapse-Proof Non-Contrastive Self-Supervised Learningcited by 7
  6. 2024A Probabilistic Model Behind Self-Supervised Learningcited by 5
  7. 2026Understanding Self-Supervised Learning via Latent Distribution Matchingcited by 4
  8. 2024Towards One Model for Classical Dimensionality Reduction: A Probabilistic Perspective on UMAP and t-SNEcited by 3
  9. 2024Multi-Token Enhancing for Vision Representation Learningcited by 3
  10. 2025DUAL: Dynamic Uncertainty-Aware Learningcited by 3
  11. 2025Transformers as Unrolled Inference in Probabilistic Laplacian Eigenmaps: An Interpretation and Potential Improvementscited by 3
  12. 2023Unifying Self-Supervised Clustering and Energy-Based Modelscited by 2
10 more
  1. 2024Beyond Spectral Decomposition: Bayesian Contrastive Learning and its Non-negative Formulation via Factor Analysiscited by 2
  2. 2024SimSiam Naming Game: A Unified Approach for Emergent Communication and Representation Learningcited by 1
  3. 2025On the Generalization of Representation Uncertainty in Earth Observationcited by 1
  4. 2023Representation Synthesis by Probabilistic Many-Valued Logic Operation in Self-Supervised Learningcited by 0
  5. 2023Unveiling the Potential of Probabilistic Embeddings in Self-Supervised Learningcited by 0
  6. 2025Self-Supervised Learning with Gaussian Processescited by 0
  7. 2026Variational Contrastive Learning for Skeleton-based Action Recognitioncited by 0
  8. 2026Joint Embedding Variational Bayescited by 0
  9. 2026Sensory Precision Inference for Multimodal Arbitration under Uncertaintycited by 0
  10. 2026Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisancecited by 0