mlsanityData to 14 Oct 2026

Few-shot Metric Learning: Online Adaptation of Embedding for Retrieval

arXiv 2211.07116 ↗First posted 14 Nov 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Metric learning aims to build a distance metric typically by learning an effective embedding function that maps similar objects into nearby points in its embedding space. Despite recent advances in deep metric learning, it remains challenging for the learned metric to generalize to unseen classes with a substantial domain gap. To tackle the issue, we explore a new problem of few-shot metric learning that aims to adapt the embedding function to the target domain with only a few annotated data. We introduce three few-shot metric learning baselines and propose the Channel-Rectifier Meta-Learning (CRML), which effectively adapts the metric space online by adjusting channels of intermediate layers. Experimental analyses on miniImageNet, CUB-200-2011, MPII, as well as a new dataset, miniDeepFashion, demonstrate that our method consistently improves the learned metric by adapting it to target classes and achieves a greater gain in image retrieval when the domain gap from the source classes is larger.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 14 Nov 2022.

Builds on

29 of 46 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2019A Closer Look at Few-shot Classificationcited by 684
  7. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  8. 2014Deep metric learning using Triplet networkcited by 422
  9. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  10. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  11. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  12. 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
17 more
  1. 2017No Fuss Distance Metric Learning using Proxiescited by 226
  2. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  3. 2014Learning Fine-grained Image Similarity with Deep Rankingcited by 190
  4. 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
  5. 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
  6. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  7. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  8. 2021Relational Embedding for Few-Shot Classificationcited by 74
  9. 2015Learning Descriptors for Object Recognition and 3D Pose Estimationcited by 60
  10. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  11. 2017Few-Shot Learning Through an Information Retrieval Lenscited by 51
  12. 2018Few-Shot Learning with Metric-Agnostic Conditional Embeddingscited by 40
  13. 2019Deep Metric Learning Beyond Binary Supervisioncited by 36
  14. 2021Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifiercited by 32
  15. 2021Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learningcited by 17
  16. 2022CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classificationcited by 9
  17. 2017Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videoscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 3; 2026: 1.

8 papers.

  1. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  2. 2023Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationcited by 11
  3. 2025Generalization-Enhanced Few-Shot Object Detection in Remote Sensingcited by 4
  4. 2024Cross-System Categorization of Abnormal Traces in Microservice-Based Systems via Meta-Learningcited by 2
  5. 2024Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognitioncited by 2
  6. 2025MvBody: Multi-View-Based Hybrid Transformer Using Optical 3D Body Scan for Explainable Cesarean Section Predictioncited by 1
  7. 2025Memory-Modular Classification: Learning to Generalize with Memory Replacementcited by 0
  8. 2026STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognitioncited by 0