mlsanityData to 14 Oct 2026

Learning Representations for New Sound Classes With Continual Self-Supervised Learning

arXiv 2205.07390 ↗First posted 15 May 2022eess.AS cs.LG cs.SDcited by 8

Not on the map. Why?

Abstract (arXiv)

In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 42 of its 50 references that are in the map. First posted on arXiv 15 May 2022.

Builds on

42 of 50 references.

References · 42

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  7. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  9. 2016Learning without Forgettingcited by 2,496
  10. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  11. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  12. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
30 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  2. 2016Progressive Neural Networkscited by 1,361
  3. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  4. 2017Continual Learning with Deep Generative Replaycited by 1,158
  5. 2016Colorful Image Colorizationcited by 1,114
  6. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  7. 2020VGGSound: A Large-scale Audio-Visual Datasetcited by 648
  8. 2019Three scenarios for continual learningcited by 614
  9. 2018End-to-End Incremental Learningcited by 597
  10. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 574
  11. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 406
  12. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 372
  13. 2020Few-Shot Class-Incremental Learningcited by 251
  14. 2018Online Structured Laplace Approximations For Overcoming Catastrophic Forgettingcited by 201
  15. 2021SSAST: Self-Supervised Audio Spectrogram Transformercited by 169
  16. 2021Self-Supervised Models are Continual Learnerscited by 149
  17. 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 130
  18. 2021BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representationcited by 106
  19. 2021Representational Continuity for Unsupervised Continual Learningcited by 95
  20. 2018A multi-device dataset for urban acoustic scene classificationcited by 75
  21. 2020Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representationcited by 59
  22. 2021Self-Supervised Training Enhances Online Continual Learningcited by 54
  23. 2022A Closer Look at Rehearsal-Free Continual Learningcited by 54
  24. 2021Continual Learning for Fake Audio Detectioncited by 27
  25. 2021An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learningcited by 19
  26. 2019Continual Learning of New Sound Classes using Generative Replaycited by 11
  27. 2020Self-Supervised Learning Aided Class-Incremental Lifelong Learningcited by 11
  28. 2021Self-Supervised Class Incremental Learningcited by 8
  29. 2021Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approachcited by 3
  30. 2020PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 2; 2025: 1.

8 papers.

  1. 2024Continual Audio-Visual Sound Separationcited by 7
  2. 2023Self-supervised learning for infant cry analysiscited by 4
  3. 2023Unsupervised Improvement of Audio-Text Cross-Modal Representationscited by 3
  4. 2023Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understandingcited by 3
  5. 2024Characterizing Continual Learning Scenarios and Strategies for Audio Analysiscited by 3
  6. 2025Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillationcited by 2
  7. 2023DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codescited by 1
  8. 2023Continual Contrastive Spoken Language Understandingcited by 0