mlsanityData to 7 Oct 2026

AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination

arXiv 2210.14564 ↗First posted 26 Oct 2022eess.AS cs.IR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Many recent loss functions in deep metric learning are expressed with logarithmic and exponential forms, and they involve margin and scale as essential hyper-parameters. Since each data class has an intrinsic characteristic, several previous works have tried to learn embedding space close to the real distribution by introducing adaptive margins. However, there was no work on adaptive scales at all. We argue that both margin and scale should be adaptively adjustable during the training. In this paper, we propose a method called Adaptive Margin and Scale (AdaMS), where hyper-parameters of margin and scale are replaced with learnable parameters of adaptive margins and adaptive scales for each class. Our method is evaluated on Wall Street Journal dataset, and we achieve outperforming results for word discrimination tasks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

17 of 23 references.

References · 17

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  4. 2017Sampling Matters in Deep Embedding Learningcited by 285
  5. 2017No Fuss Distance Metric Learning using Proxiescited by 225
  6. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  7. 2018Deep Metric Learning with Hierarchical Triplet Losscited by 112
  8. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  9. 2016Learning Deep Embeddings with Histogram Losscited by 52
  10. 2015Deep convolutional acoustic word embeddings using word-pair side informationcited by 27
  11. 2016Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approachescited by 25
  12. 2016Multi-view Recurrent Neural Acoustic Word Embeddingscited by 20
5 more
  1. 2020Multilingual Jointly Trained Acoustic and Written Word Embeddingscited by 16
  2. 2019Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognitioncited by 15
  3. 2019P2SGrad: Refined Gradients for Optimizing Deep Face Modelscited by 14
  4. 2019Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddingscited by 6
  5. 2022Asymmetric Proxy Loss for Multi-View Acoustic Word Embeddingscited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2024Relational Proxy Loss for Audio-Text based Keyword Spottingcited by 3
  2. 2024Text-Aware Adapter for Few-Shot Keyword Spottingcited by 2
  3. 2025Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spottingcited by 1
  4. 2026MATE: Matryoshka Audio-Text Embeddings for Open-Vocabulary Keyword Spottingcited by 0