# Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization

arXiv: https://arxiv.org/abs/2403.03145 · HTML: https://mlsanity.com/paper/2403.03145/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 53 references that are in the map.
- First posted on arXiv 5 Mar 2024.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [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)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Look, Listen and Learn](https://mlsanity.com/paper/1705.08168/) (2017)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [The Sound of Pixels](https://mlsanity.com/paper/1804.03160/) (2018)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [SoundNet: Learning Sound Representations from Unlabeled Video](https://mlsanity.com/paper/1610.09001/) (2016)
- [Audio-Visual Instance Discrimination with Cross-Modal Agreement](https://mlsanity.com/paper/2004.12943/) (2020)
- [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)
- [The Sound of Motions](https://mlsanity.com/paper/1904.05979/) (2019)
- [Multiple Sound Sources Localization from Coarse to Fine](https://mlsanity.com/paper/2007.06355/) (2020)
- [Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework](https://mlsanity.com/paper/2103.11402/) (2021)
- [Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching](https://mlsanity.com/paper/2010.05466/) (2020)
- [Semantic Audio-Visual Navigation](https://mlsanity.com/paper/2012.11583/) (2020)
- [Localizing Visual Sounds the Easy Way](https://mlsanity.com/paper/2203.09324/) (2022)
- [Robust Audio-Visual Instance Discrimination](https://mlsanity.com/paper/2103.15916/) (2021)

## Built on by (most cited first, 10 of 10)

- [Active Generalized Category Discovery](https://mlsanity.com/paper/2403.04272/) (2024)
- [CoReS: Orchestrating the Dance of Reasoning and Segmentation](https://mlsanity.com/paper/2404.05673/) (2024)
- [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)
- [What's Making That Sound Right Now? Video-centric Audio-Visual Localization](https://mlsanity.com/paper/2507.04667/) (2025)
- [Unveiling Visual Biases in Audio-Visual Localization Benchmarks](https://mlsanity.com/paper/2409.06709/) (2024)
- [HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation](https://mlsanity.com/paper/2504.09876/) (2025)
- [Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence](https://mlsanity.com/paper/2412.00883/) (2024)
- [OpenAVS: Training-Free Open-Vocabulary Audio Visual Segmentation with Foundational Models](https://mlsanity.com/paper/2505.01448/) (2025)

## Abstract (arXiv)

Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without any bounding-box annotations, they struggle to achieve precise localization, especially for small objects, and suffer from blurry boundaries and false positives. Moreover, the naive semi-supervised method is poor in fully leveraging the information of abundant unlabeled data. In this paper, we propose a novel semi-supervised learning framework for AVSL, namely Dual Mean-Teacher (DMT), comprising two teacher-student structures to circumvent the confirmation bias issue. Specifically, two teachers, pre-trained on limited labeled data, are employed to filter out noisy samples via the consensus between their predictions, and then generate high-quality pseudo-labels by intersecting their confidence maps. The sufficient utilization of both labeled and unlabeled data and the proposed unbiased framework enable DMT to outperform current state-of-the-art methods by a large margin, with CIoU of 90.4% and 48.8% on Flickr-SoundNet and VGG-Sound Source, obtaining 8.9%, 9.6% and 4.6%, 6.4% improvements over self- and semi-supervised methods respectively, given only 3% positional-annotations. We also extend our framework to some existing AVSL methods and consistently boost their performance.