mlsanityData to 7 Oct 2026

PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation

arXiv 2102.01243 ↗First posted 2 Feb 2021cs.SD cs.LG eess.AScited by 81

Not on the map. Why?

Abstract (arXiv)

Audio tagging is an active research area and has a wide range of applications. Since the release of AudioSet, great progress has been made in advancing model performance, which mostly comes from the development of novel model architectures and attention modules. However, we find that appropriate training techniques are equally important for building audio tagging models with AudioSet, but have not received the attention they deserve. To fill the gap, in this work, we present PSLA, a collection of training techniques that can noticeably boost the model accuracy including ImageNet pretraining, balanced sampling, data augmentation, label enhancement, model aggregation and their design choices. By training an EfficientNet with these techniques, we obtain a single model (with 13.6M parameters) and an ensemble model that achieve mean average precision (mAP) scores of 0.444 and 0.474 on AudioSet, respectively, outperforming the previous best system of 0.439 with 81M parameters. In addition, our model also achieves a new state-of-the-art mAP of 0.567 on FSD50K.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). Builds on 35 of its 61 references that are in the map. First posted on arXiv 2 Feb 2021.

Builds on

35 of 61 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  11. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  12. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
23 more
  1. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  2. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 563
  3. 2018Rethinking ImageNet Pre-trainingcited by 376
  4. 2020FSD50K: An Open Dataset of Human-Labeled Sound Eventscited by 339
  5. 2019An Unsupervised Autoregressive Model for Speech Representation Learningcited by 185
  6. 2020Contrastive Learning of General-Purpose Audio Representationscited by 168
  7. 2020Towards Learning a Universal Non-Semantic Representation of Speechcited by 84
  8. 2018There Are Many Consistent Explanations of Unlabeled Data: Why You Should Averagecited by 82
  9. 2017Learning from Between-class Examples for Deep Sound Recognitioncited by 53
  10. 2017Between-class Learning for Image Classificationcited by 50
  11. 2020Rethinking CNN Models for Audio Classificationcited by 48
  12. 2017Unsupervised Learning of Semantic Audio Representationscited by 44
  13. 2018A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labelingcited by 37
  14. 2020ESResNet: Environmental Sound Classification Based on Visual Domain Modelscited by 31
  15. 2017Knowledge Transfer from Weakly Labeled Audio using Convolutional Neural Network for Sound Events and Scenescited by 20
  16. 2019Weakly Labelled AudioSet Tagging with Attention Neural Networkscited by 17
  17. 2017Audio Set classification with attention model: A probabilistic perspectivecited by 13
  18. 2018A Closer Look at Weak Label Learning for Audio Eventscited by 11
  19. 2019Urban Sound Tagging using Convolutional Neural Networkscited by 7
  20. 2020Addressing Missing Labels in Large-Scale Sound Event Recognition Using a Teacher-Student Framework With Loss Maskingcited by 7
  21. 2017Reducing Model Complexity for DNN Based Large-Scale Audio Classificationcited by 4
  22. 2018Multi-level Attention Model for Weakly Supervised Audio Classificationcited by 4
  23. 2019HODGEPODGE: Sound event detection based on ensemble of semi-supervised learning methodscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 21; 2023: 21; 2024: 15; 2025: 11; 2026: 9.

81 papers.

Sort:

By area:

  1. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  2. 2022BEATs: Audio Pre-Training with Acoustic Tokenizerscited by 378
  3. 2022Masked Autoencoders that Listencited by 271
  4. 2021Efficient Training of Audio Transformers with Patchoutcited by 222
  5. 2021Wav2CLIP: Learning Robust Audio Representations From CLIPcited by 210
  6. 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detectioncited by 174
  7. 2022Contrastive Audio-Visual Masked Autoencodercited by 142
  8. 2023Joint Audio and Speech Understandingcited by 99
  9. 2022HEAR: Holistic Evaluation of Audio Representationscited by 77
  10. 2022Vision Transformers are Parameter-Efficient Audio-Visual Learnerscited by 72
  11. 2023UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognitioncited by 64
  12. 2022Vocalsound: A Dataset for Improving Human Vocal Sounds Recognitioncited by 62
38 more
  1. 2024EAT: Self-Supervised Pre-Training with Efficient Audio Transformercited by 52
  2. 2023A-JEPA: Joint-Embedding Predictive Architecture Can Listencited by 50
  3. 2022Audiovisual Masked Autoencoderscited by 47
  4. 2022ECLIPSE: Efficient Long-range Video Retrieval using Sight and Soundcited by 39
  5. 2023Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusioncited by 39
  6. 2022Supervised and Unsupervised Learning of Audio Representations for Music Understandingcited by 34
  7. 2022XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learningcited by 30
  8. 2021Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Datacited by 27
  9. 2022Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillationcited by 25
  10. 2023Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Taskscited by 25
  11. 2024Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patchescited by 22
  12. 2022UAVM: Towards Unifying Audio and Visual Modelscited by 20
  13. 2023Multiscale Audio Spectrogram Transformer for Efficient Audio Classificationcited by 16
  14. 2022CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classificationcited by 12
  15. 2024Siamese Vision Transformers are Scalable Audio-visual Learnerscited by 12
  16. 2024Fourier Head: Helping Large Language Models Learn Complex Probability Distributionscited by 10
  17. 2022Simple Pooling Front-ends For Efficient Audio Classificationcited by 8
  18. 2024PALM: Few-Shot Prompt Learning for Audio Language Modelscited by 8
  19. 2024Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representationscited by 8
  20. 2024Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalitiescited by 7
  21. 2024Towards Signal Processing In Large Language Modelscited by 7
  22. 2025CogniAlign: Word-Level Multimodal Speech Alignment with Gated Cross-Attention for Alzheimer's Detectioncited by 6
  23. 2024Generalization in birdsong classification: impact of transfer learning methods and dataset characteristicscited by 5
  24. 2022Learning Temporal Resolution in Spectrogram for Audio Classificationcited by 4
  25. 2023Dataset balancing can hurt model performancecited by 4
  26. 2023ATGNN: Audio Tagging Graph Neural Networkcited by 4
  27. 2022Segment-level Metric Learning for Few-shot Bioacoustic Event Detectioncited by 3
  28. 2022Play It Back: Iterative Attention for Audio Recognitioncited by 3
  29. 2023A Comparative Study of Pre-trained Speech and Audio Embeddings for Speech Emotion Recognitioncited by 3
  30. 2023MMViT: Multiscale Multiview Vision Transformerscited by 3
  31. 2023LEAN: Light and Efficient Audio Classification Networkcited by 3
  32. 2023Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Modelscited by 3
  33. 2024Pre-training with Synthetic Patterns for Audiocited by 3
  34. 2024Whisper-GPT -- Continuous Discrete Hybrid Representation Language Models For Speech And Musiccited by 2
  35. 2025NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversioncited by 2
  36. 2021Study of positional encoding approaches for Audio Spectrogram Transformerscited by 1
  37. 2022UFRC: A Unified Framework for Reliable COVID-19 Detection on Crowdsourced Cough Audiocited by 1
  38. 2022Ontology-aware Learning and Evaluation for Audio Taggingcited by 1

50 most cited of 81 All 81 (JSON)