mlsanityData to 14 Oct 2026

Learning Deep Embeddings with Histogram Loss

arXiv 1611.00822 ↗First posted 2 Nov 2016cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

We suggest a loss for learning deep embeddings. The new loss does not introduce parameters that need to be tuned and results in very good embeddings across a range of datasets and problems. The loss is computed by estimating two distribution of similarities for positive (matching) and negative (non-matching) sample pairs, and then computing the probability of a positive pair to have a lower similarity score than a negative pair based on the estimated similarity distributions. We show that such operations can be performed in a simple and piecewise-differentiable manner using 1D histograms with soft assignment operations. This makes the proposed loss suitable for learning deep embeddings using stochastic optimization. In the experiments, the new loss performs favourably compared to recently proposed alternatives.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 21; 2022: 12; 2023: 5; 2024: 8; 2025: 3; 2026: 3.

52 papers.

Sort:

By area:

  1. 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 124
  2. 2022RankSim: Ranking Similarity Regularization for Deep Imbalanced Regressioncited by 52
  3. 2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
  4. 2021Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmarkcited by 47
  5. 2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
  6. 2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
  7. 2021Towards Interpretable Deep Metric Learning with Structural Matchingcited by 30
  8. 2021Robust and Decomposable Average Precision for Image Retrievalcited by 19
  9. 2023Optimization of Rank Losses for Image Retrievalcited by 10
  10. 2024Not All Pairs are Equal: Hierarchical Learning for Average-Precision-Oriented Video Retrievalcited by 9
  11. 2021Adaptive Hierarchical Similarity Metric Learning with Noisy Labelscited by 8
  12. 2022Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stabilitycited by 8
38 more
  1. 2022Contrastive Bayesian Analysis for Deep Metric Learningcited by 8
  2. 2021LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learningcited by 7
  3. 2021Multi-level Distance Regularization for Deep Metric Learningcited by 6
  4. 2021Improving Deep Metric Learning by Divide and Conquercited by 5
  5. 2022DAS: Densely-Anchored Sampling for Deep Metric Learningcited by 5
  6. 2021Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enoughcited by 4
  7. 2022Learning Pair Potentials using Differentiable Simulationscited by 4
  8. 2022AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discriminationcited by 4
  9. 2023Center Contrastive Loss for Metric Learningcited by 4
  10. 2024Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matchingcited by 4
  11. 2024GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learningcited by 4
  12. 2021Rethinking Deep Contrastive Learning with Embedding Memorycited by 3
  13. 2021The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regressioncited by 3
  14. 2021Atlas Based Representation and Metric Learning on Manifoldscited by 3
  15. 2024Towards Fine-Grained Webpage Fingerprinting at Scalecited by 3
  16. 2025Automatic Grid Updates for Kolmogorov-Arnold Networks using Layer Histogramscited by 3
  17. 2021A Framework to Enhance Generalization of Deep Metric Learning methods using General Discriminative Feature Learning and Class Adversarial Neural Networkscited by 2
  18. 2021Ensemble of Loss Functions to Improve Generalizability of Deep Metric Learning methodscited by 2
  19. 2023On the Stability and Generalization of Triplet Learningcited by 2
  20. 2023Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detectioncited by 2
  21. 2024OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognitioncited by 2
  22. 2025Decision-centric fairness: Evaluation and optimization for resource allocation problemscited by 2
  23. 2025Rethinking Image Histogram Matching for Image Classificationcited by 2
  24. 2021A Decidability-Based Loss Functioncited by 1
  25. 2022Rendering Nighttime Image Via Cascaded Color and Brightness Compensationcited by 1
  26. 2022A Survey of Face Recognitioncited by 1
  27. 2024Controllable Relation Disentanglement for Few-Shot Class-Incremental Learningcited by 1
  28. 2021Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learningcited by 0
  29. 2021GB-CosFace: Rethinking Softmax-based Face Recognition from the Perspective of Open Set Classificationcited by 0
  30. 2021HBReID: Harder Batch for Re-identificationcited by 0
  31. 2022Data-Driven Estimation of Capacity Upper Boundscited by 0
  32. 2022Deep Metric Color Embeddings for Splicing Localization in Severely Degraded Imagescited by 0
  33. 2022Self-Supervised Pretraining of Graph Neural Network for the Retrieval of Related Mathematical Expressions in Scientific Articlescited by 0
  34. 2022Learning Deep Optimal Embeddings with Sinkhorn Divergencescited by 0
  35. 2023Enhancing Face Recognition with Latent Space Data Augmentation and Facial Posture Reconstructioncited by 0
  36. 2024Brain-Shift: Unsupervised Pseudo-Healthy Brain Synthesis for Novel Biomarker Extraction in Chronic Subdural Hematomacited by 0
  37. 2024DAAL: Density-Aware Adaptive Line Margin Loss for Multi-Modal Deep Metric Learningcited by 0
  38. 2026SSR: A Generic Framework for Text-Aided Map Compression for Localizationcited by 0

50 most cited of 52 All 52 (JSON)