# Multi-Branch Learning for Weakly-Labeled Sound Event Detection

arXiv: https://arxiv.org/abs/2002.09661 · HTML: https://mlsanity.com/paper/2002.09661/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2020.

## Built on by (most cited first, 3 of 3)

- [Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection](https://mlsanity.com/paper/2110.02011/) (2021)
- [Joint framework with deep feature distillation and adaptive focal loss for weakly supervised audio tagging and acoustic event detection](https://mlsanity.com/paper/2103.12388/) (2021)
- [Shared Representation Learning for Reference-Guided Targeted Sound Detection](https://mlsanity.com/paper/2603.17025/) (2026)

## Abstract (arXiv)

There are two sub-tasks implied in the weakly-supervised SED: audio tagging and event boundary detection. Current methods which combine multi-task learning with SED requires annotations both for these two sub-tasks. Since there are only annotations for audio tagging available in weakly-supervised SED, we design multiple branches with different learning purposes instead of pursuing multiple tasks. Similar to multiple tasks, multiple different learning purposes can also prevent the common feature which the multiple branches share from overfitting to any one of the learning purposes. We design these multiple different learning purposes based on combinations of different MIL strategies and different pooling methods. Experiments on the DCASE 2018 Task 4 dataset and the URBAN-SED dataset both show that our method achieves competitive performance.