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

arXiv: https://arxiv.org/abs/1810.09050 · HTML: https://mlsanity.com/paper/1810.09050/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2018.

## Built on by (most cited first, 30 of 38)

- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection](https://mlsanity.com/paper/2202.00874/) (2022)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [Multi-Format Contrastive Learning of Audio Representations](https://mlsanity.com/paper/2103.06508/) (2021)
- [MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing](https://mlsanity.com/paper/2111.12374/) (2021)
- [Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2204.11573/) (2022)
- [Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks](https://mlsanity.com/paper/2110.07313/) (2021)
- [Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.12570/) (2022)
- [FedMM: Federated Multi-Modal Learning with Modality Heterogeneity in Computational Pathology](https://mlsanity.com/paper/2402.15858/) (2024)
- [Multiscale Audio Spectrogram Transformer for Efficient Audio Classification](https://mlsanity.com/paper/2303.10757/) (2023)
- [A Comparative Analysis of Decision-Level Fusion for Multimodal Driver Behaviour Understanding](https://mlsanity.com/paper/2204.04734/) (2022)
- [CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification](https://mlsanity.com/paper/2203.06760/) (2022)
- [Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2307.02041/) (2023)
- [Grounded Image Text Matching with Mismatched Relation Reasoning](https://mlsanity.com/paper/2308.01236/) (2023)
- [Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection](https://mlsanity.com/paper/2110.02011/) (2021)
- [MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection](https://mlsanity.com/paper/2408.08673/) (2024)
- [Audiovisual transfer learning for audio tagging and sound event detection](https://mlsanity.com/paper/2106.05408/) (2021)
- [Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Study](https://mlsanity.com/paper/2505.01109/) (2025)
- [Voice activity detection in the wild: A data-driven approach using teacher-student training](https://mlsanity.com/paper/2105.04065/) (2021)
- [Federated Self-Supervised Learning for Acoustic Event Classification](https://mlsanity.com/paper/2203.11997/) (2022)
- [TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification](https://mlsanity.com/paper/2312.14149/) (2023)
- [Play It Back: Iterative Attention for Audio Recognition](https://mlsanity.com/paper/2210.11328/) (2022)
- [NeuroView-RNN: It's About Time](https://mlsanity.com/paper/2202.11811/) (2022)
- [Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection](https://mlsanity.com/paper/2307.09457/) (2023)
- [Unsupervised Learning of Multi-level Structures for Anomaly Detection](https://mlsanity.com/paper/2104.12102/) (2021)
- [Do sound event representations generalize to other audio tasks? A case study in audio transfer learning](https://mlsanity.com/paper/2106.11335/) (2021)
- [Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Network](https://mlsanity.com/paper/2204.08084/) (2022)
- [Go Beyond Multiple Instance Neural Networks: Deep-learning Models based on Local Pattern Aggregation](https://mlsanity.com/paper/2205.14428/) (2022)
- [Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study](https://mlsanity.com/paper/2110.03174/) (2021)
- [Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework](https://mlsanity.com/paper/2206.13476/) (2022)

## 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.