mlsanityData to 7 Oct 2026

Realigned Softmax Warping for Deep Metric Learning

arXiv 2408.15656 ↗First posted 28 Aug 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Metric Learning (DML) loss functions traditionally aim to control the forces of separability and compactness within an embedding space so that the same class data points are pulled together and different class ones are pushed apart. Within the context of DML, a softmax operation will typically normalize distances into a probability for optimization, thus coupling all the push/pull forces together. This paper proposes a potential new class of loss functions that operate within a euclidean domain and aim to take full advantage of the coupled forces governing embedding space formation under a softmax. These forces of compactness and separability can be boosted or mitigated within controlled locations at will by using a warping function. In this work, we provide a simple example of a warping function and use it to achieve competitive, state-of-the-art results on various metric learning benchmarks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 56 of its 78 references that are in the map. First posted on arXiv 28 Aug 2024.

Builds on

56 of 78 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2016Layer Normalizationcited by 5,579
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  5. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  6. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  7. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  8. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  9. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  10. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 332
  11. 2020A Metric Learning Reality Checkcited by 317
  12. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
38 more
  1. 2017Sampling Matters in Deep Embedding Learningcited by 285
  2. 2017Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environmentscited by 258
  3. 2017No Fuss Distance Metric Learning using Proxiescited by 225
  4. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  5. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 184
  6. 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
  7. 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
  8. 2020ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysiscited by 107
  9. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  10. 2020Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrievalcited by 98
  11. 2017L2-constrained Softmax Loss for Discriminative Face Verificationcited by 96
  12. 2017Smart Mining for Deep Metric Learningcited by 96
  13. 2019Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidthcited by 88
  14. 2019Optimizing Rank-based Metrics with Blackbox Differentiationcited by 58
  15. 2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
  16. 2019Divide and Conquer the Embedding Space for Metric Learningcited by 39
  17. 2017Semantic Instance Segmentation via Deep Metric Learningcited by 37
  18. 2021Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identificationcited by 37
  19. 2020Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxiescited by 36
  20. 2021Learning Intra-Batch Connections for Deep Metric Learningcited by 34
  21. 2022Non-isotropy Regularization for Proxy-based Deep Metric Learningcited by 33
  22. 2021Towards Interpretable Deep Metric Learning with Structural Matchingcited by 30
  23. 2022HIER: Metric Learning Beyond Class Labels via Hierarchical Regularizationcited by 26
  24. 2021It Takes Two to Tango: Mixup for Deep Metric Learningcited by 23
  25. 2021Deep Relational Metric Learningcited by 22
  26. 2021Learning with Memory-based Virtual Classes for Deep Metric Learningcited by 21
  27. 2019The Group Loss for Deep Metric Learningcited by 20
  28. 2021Robust and Decomposable Average Precision for Image Retrievalcited by 19
  29. 2022A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learningcited by 19
  30. 2021Hierarchical Proxy-based Loss for Deep Metric Learningcited by 18
  31. 2019Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learningcited by 10
  32. 2024Towards Improved Proxy-based Deep Metric Learning via Data-Augmented Domain Adaptationcited by 9
  33. 2022Contrastive Bayesian Analysis for Deep Metric Learningcited by 8
  34. 2023Threshold-Consistent Margin Loss for Open-World Deep Metric Learningcited by 7
  35. 2024Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learningcited by 6
  36. 2022Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimizationcited by 5
  37. 2021Multi-Head Deep Metric Learning Using Global and Local Representationscited by 4
  38. 2023Center Contrastive Loss for Metric Learningcited by 4

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.