# Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging

arXiv: https://arxiv.org/abs/2503.21826 · HTML: https://mlsanity.com/paper/2503.21826/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 13 of 13)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline](https://mlsanity.com/paper/1807.09902/) (2018)
- [CED: Consistent ensemble distillation for audio tagging](https://mlsanity.com/paper/2308.11957/) (2023)
- [Audio tagging with noisy labels and minimal supervision](https://mlsanity.com/paper/1906.02975/) (2019)
- [Adapting a ConvNeXt model to audio classification on AudioSet](https://mlsanity.com/paper/2306.00830/) (2023)
- [ATST: Audio Representation Learning with Teacher-Student Transformer](https://mlsanity.com/paper/2204.12076/) (2022)
- [Audio Tagging by Cross Filtering Noisy Labels](https://mlsanity.com/paper/2007.08165/) (2020)

## Abstract (arXiv)

AudioSet is one of the most used and largest datasets in audio tagging, containing about 2 million audio samples that are manually labeled with 527 event categories organized into an ontology. However, the annotations contain inconsistencies, particularly where categories that should be labeled as positive according to the ontology are frequently mislabeled as negative. To address this issue, we apply Hierarchical Label Propagation (HLP), which propagates labels up the ontology hierarchy, resulting in a mean increase in positive labels per audio clip from 1.98 to 2.39 and affecting 109 out of the 527 classes. Our results demonstrate that HLP provides performance benefits across various model architectures, including convolutional neural networks (PANN's CNN6 and ConvNeXT) and transformers (PaSST), with smaller models showing more improvements. Finally, on FSD50K, another widely used dataset, models trained on AudioSet with HLP consistently outperformed those trained without HLP. Our source code will be made available on GitHub.