# Audio Set classification with attention model: A probabilistic perspective

arXiv: https://arxiv.org/abs/1711.00927 · HTML: https://mlsanity.com/paper/1711.00927/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2017.

## Built on by (most cited first, 14 of 14)

- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Contrastive Positive Sample Propagation along the Audio-Visual Event Line](https://mlsanity.com/paper/2211.09980/) (2022)
- [InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions](https://mlsanity.com/paper/2412.09596/) (2024)
- [MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing](https://mlsanity.com/paper/2111.12374/) (2021)
- [Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling](https://mlsanity.com/paper/2406.00919/) (2024)
- [Improving Audio-Visual Video Parsing with Pseudo Visual Labels](https://mlsanity.com/paper/2303.02344/) (2023)
- [Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer](https://mlsanity.com/paper/2112.08995/) (2021)
- [Audio-Visual Transformer Based Crowd Counting](https://mlsanity.com/paper/2109.01926/) (2021)
- [Voice activity detection in the wild: A data-driven approach using teacher-student training](https://mlsanity.com/paper/2105.04065/) (2021)
- [InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries](https://mlsanity.com/paper/2409.19689/) (2024)
- [RealDESED: A Real-World Domestic Sound Event Detection Benchmark](https://mlsanity.com/paper/2607.16736/) (2026)
- [Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study](https://mlsanity.com/paper/2110.03174/) (2021)

## Abstract (arXiv)

This paper investigates the classification of the Audio Set dataset. Audio Set is a large scale weakly labelled dataset of sound clips. Previous work used multiple instance learning (MIL) to classify weakly labelled data. In MIL, a bag consists of several instances, and a bag is labelled positive if at least one instances in the audio clip is positive. A bag is labelled negative if all the instances in the bag are negative. We propose an attention model to tackle the MIL problem and explain this attention model from a novel probabilistic perspective. We define a probability space on each bag, where each instance in the bag has a trainable probability measure for each class. Then the classification of a bag is the expectation of the classification output of the instances in the bag with respect to the learned probability measure. Experimental results show that our proposed attention model modeled by fully connected deep neural network obtains mAP of 0.327 on Audio Set dataset, outperforming the Google's baseline of 0.314 and recurrent neural network of 0.325.