mlsanityData to 7 Oct 2026

Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval

arXiv 2302.01332 ↗First posted 2 Feb 2023cs.LG cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

We propose the first Bayesian encoder for metric learning. Rather than relying on neural amortization as done in prior works, we learn a distribution over the network weights with the Laplace Approximation. We actualize this by first proving that the contrastive loss is a valid log-posterior. We then propose three methods that ensure a positive definite Hessian. Lastly, we present a novel decomposition of the Generalized Gauss-Newton approximation. Empirically, we show that our Laplacian Metric Learner (LAM) estimates well-calibrated uncertainties, reliably detects out-of-distribution examples, and yields state-of-the-art predictive performance.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 2 Feb 2023.

Builds on

32 of 53 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  7. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  8. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  9. 2015Weight Uncertainty in Neural Networkscited by 554
  10. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  11. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  12. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
20 more
  1. 2020A Metric Learning Reality Checkcited by 317
  2. 2018Deep Face Recognition: A Surveycited by 275
  3. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  4. 2019Limitations of the Empirical Fisher Approximation for Natural Gradient Descentcited by 213
  5. 2019Probabilistic Face Embeddingscited by 171
  6. 2021Probabilistic Embeddings for Cross-Modal Retrievalcited by 150
  7. 2020Data Uncertainty Learning in Face Recognitioncited by 134
  8. 2014Word Representations via Gaussian Embeddingcited by 96
  9. 2019Polysemous Visual-Semantic Embedding for Cross-Modal Retrievalcited by 83
  10. 2019BackPACK: Packing more into backpropcited by 77
  11. 2019Reliable training and estimation of variance networkscited by 63
  12. 2018Modeling Uncertainty with Hedged Instance Embeddingcited by 52
  13. 2019View-Invariant Probabilistic Embedding for Human Posecited by 47
  14. 2020Bayesian Triplet Loss: Uncertainty Quantification in Image Retrievalcited by 31
  15. 2019Hotels-50K: A Global Hotel Recognition Datasetcited by 13
  16. 2022Laplacian Autoencoders for Learning Stochastic Representationscited by 10
  17. 2019Unsupervised Data Uncertainty Learning in Visual Retrieval Systemscited by 7
  18. 2015Learning Concept Embeddings with Combined Human-Machine Expertisecited by 6
  19. 2019Exploring Uncertainty in Conditional Multi-Modal Retrieval Systemscited by 4
  20. 2022Searching for Structure in Unfalsifiable Claimscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 5.

9 papers.

  1. 2023Improved Probabilistic Image-Text Representationscited by 40
  2. 2024Reparameterization invariance in approximate Bayesian inferencecited by 17
  3. 2025VIKING: Deep variational inference with stochastic projectionscited by 3
  4. 2024Towards certifiable AI in aviation: landscape, challenges, and opportunitiescited by 2
  5. 2024Corpus-informed Retrieval Augmented Generation of Clarifying Questionscited by 2
  6. 2025Quantifying the uncertainty of model-based synthetic image quality metricscited by 1
  7. 2025PEdger++: Practical Edge Detection via Assembling Cross Informationcited by 0
  8. 2025UncertainGen: Uncertainty-Aware Representations of DNA Sequences for Metagenomic Binningcited by 0
  9. 2025Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shiftscited by 0