# Cross Pseudo-Labeling for Semi-Supervised Audio-Visual Source Localization

arXiv: https://arxiv.org/abs/2403.03095 · HTML: https://mlsanity.com/paper/2403.03095/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 5 Mar 2024.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [SoundNet: Learning Sound Representations from Unlabeled Video](https://mlsanity.com/paper/1610.09001/) (2016)
- [Learning to Localize Sound Source in Visual Scenes](https://mlsanity.com/paper/1803.03849/) (2018)
- [Localizing Visual Sounds the Hard Way](https://mlsanity.com/paper/2104.02691/) (2021)
- [Multiple Sound Sources Localization from Coarse to Fine](https://mlsanity.com/paper/2007.06355/) (2020)
- [Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching](https://mlsanity.com/paper/2010.05466/) (2020)
- [Localizing Visual Sounds the Easy Way](https://mlsanity.com/paper/2203.09324/) (2022)
- [A Closer Look at Weakly-Supervised Audio-Visual Source Localization](https://mlsanity.com/paper/2209.09634/) (2022)
- [Mix and Localize: Localizing Sound Sources in Mixtures](https://mlsanity.com/paper/2211.15058/) (2022)
- [Audio-Visual Grouping Network for Sound Localization from Mixtures](https://mlsanity.com/paper/2303.17056/) (2023)
- [Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning](https://mlsanity.com/paper/2303.11302/) (2023)
- [Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation](https://mlsanity.com/paper/2206.12772/) (2022)
- [Class-aware Sounding Objects Localization via Audiovisual Correspondence](https://mlsanity.com/paper/2112.11749/) (2021)
- [Learning Sound Localization Better From Semantically Similar Samples](https://mlsanity.com/paper/2202.03007/) (2022)
- [Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications](https://mlsanity.com/paper/1911.09649/) (2019)
- [Open-world machine learning: A review and new outlooks](https://mlsanity.com/paper/2403.01759/) (2024)
- [Visual Sound Localization in the Wild by Cross-Modal Interference Erasing](https://mlsanity.com/paper/2202.06406/) (2022)
- [Active Audio-Visual Separation of Dynamic Sound Sources](https://mlsanity.com/paper/2202.00850/) (2022)
- [MarginNCE: Robust Sound Localization with a Negative Margin](https://mlsanity.com/paper/2211.01966/) (2022)
- [Towards Trustworthy Dataset Distillation](https://mlsanity.com/paper/2307.09165/) (2023)

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

- [ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery](https://mlsanity.com/paper/2504.03755/) (2025)
- [Happy: A Debiased Learning Framework for Continual Generalized Category Discovery](https://mlsanity.com/paper/2410.06535/) (2024)
- [Aligned Better, Listen Better for Audio-Visual Large Language Models](https://mlsanity.com/paper/2504.02061/) (2025)

## Abstract (arXiv)

Audio-Visual Source Localization (AVSL) is the task of identifying specific sounding objects in the scene given audio cues. In our work, we focus on semi-supervised AVSL with pseudo-labeling. To address the issues with vanilla hard pseudo-labels including bias accumulation, noise sensitivity, and instability, we propose a novel method named Cross Pseudo-Labeling (XPL), wherein two models learn from each other with the cross-refine mechanism to avoid bias accumulation. We equip XPL with two effective components. Firstly, the soft pseudo-labels with sharpening and pseudo-label exponential moving average mechanisms enable models to achieve gradual self-improvement and ensure stable training. Secondly, the curriculum data selection module adaptively selects pseudo-labels with high quality during training to mitigate potential bias. Experimental results demonstrate that XPL significantly outperforms existing methods, achieving state-of-the-art performance while effectively mitigating confirmation bias and ensuring training stability.