mlsanityData to 7 Oct 2026

A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling

arXiv 1810.09050 ↗First posted 22 Oct 2018cs.SD eess.AScited by 37

Not on the map. Why?

Abstract (arXiv)

Sound event detection (SED) entails two subtasks: recognizing what types of sound events are present in an audio stream (audio tagging), and pinpointing their onset and offset times (localization). In the popular multiple instance learning (MIL) framework for SED with weak labeling, an important component is the pooling function. This paper compares five types of pooling functions both theoretically and experimentally, with special focus on their performance of localization. Although the attention pooling function is currently receiving the most attention, we find the linear softmax pooling function to perform the best among the five. Using this pooling function, we build a neural network called TALNet. It is the first system to reach state-of-the-art audio tagging performance on Audio Set, while exhibiting strong localization performance on the DCASE 2017 challenge at the same time.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 13; 2023: 5; 2024: 3; 2025: 2; 2026: 5.

37 papers.

Sort:

By area:

  1. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 718
  2. 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detectioncited by 174
  3. 2021PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregationcited by 81
  4. 2021Multi-Format Contrastive Learning of Audio Representationscited by 39
  5. 2021MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsingcited by 39
  6. 2022Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsingcited by 29
  7. 2021Conformer-Based Self-Supervised Learning for Non-Speech Audio Taskscited by 22
  8. 2022Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalizationcited by 17
  9. 2024FedMM: Federated Multi-Modal Learning with Modality Heterogeneity in Computational Pathologycited by 17
  10. 2023Multiscale Audio Spectrogram Transformer for Efficient Audio Classificationcited by 16
  11. 2022A Comparative Analysis of Decision-Level Fusion for Multimodal Driver Behaviour Understandingcited by 14
  12. 2022CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classificationcited by 12
25 more
  1. 2023Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsingcited by 11
  2. 2023Grounded Image Text Matching with Mismatched Relation Reasoningcited by 8
  3. 2021Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detectioncited by 7
  4. 2024MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detectioncited by 7
  5. 2021Audiovisual transfer learning for audio tagging and sound event detectioncited by 6
  6. 2025Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Studycited by 6
  7. 2022Federated Self-Supervised Learning for Acoustic Event Classificationcited by 5
  8. 2023TagAlign: Improving Vision-Language Alignment with Multi-Tag Classificationcited by 5
  9. 2022Play It Back: Iterative Attention for Audio Recognitioncited by 3
  10. 2022NeuroView-RNN: It's About Timecited by 2
  11. 2023Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detectioncited by 2
  12. 2021Unsupervised Learning of Multi-level Structures for Anomaly Detectioncited by 1
  13. 2021Do sound event representations generalize to other audio tasks? A case study in audio transfer learningcited by 1
  14. 2022Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Networkcited by 1
  15. 2022Go Beyond Multiple Instance Neural Networks: Deep-learning Models based on Local Pattern Aggregationcited by 1
  16. 2021Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Studycited by 0
  17. 2022Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Frameworkcited by 0
  18. 2022Deep Multiple Instance Learning For Forecasting Stock Trends Using Financial Newscited by 0
  19. 2024Automatic Labels are as Effective as Manual Labels in Biomedical Images Classification with Deep Learningcited by 0
  20. 2025Exploring Performance-Complexity Trade-Offs in Sound Event Detection Modelscited by 0
  21. 2026WS-IMUBench: Can Weakly Supervised Methods from Audio, Image, and Video Be Adapted for IMU-based Temporal Action Localization?cited by 0
  22. 2026Weakly Supervised Contrastive Learning for Histopathology Patch Embeddingscited by 0
  23. 2026Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Videocited by 0
  24. 2026Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretrainingcited by 0
  25. 2026MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Trainingcited by 0