Research map / Label-efficient and robust learning / Semi-supervised learning
Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization
Yuxin Guo, Shijie Ma, Hu Su, Zhiqing Wang, Yuhao Zhao, Wei Zou, Siyang Sun, Yun Zheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use two backbones (SoundNet+VGGish) instead of SoundNet only (ablation) | DMT · Flickr-SoundNet Flickr 144k | CIoU: 80.20 -> 82.20 | Improved |
| use two backbones instead of VGGish only (ablation) | DMT · Flickr-SoundNet Flickr 144k | CIoU: 81.80 -> 82.20 | Improved |
| add EMA to dual teachers (ablation) | DMT · Flickr-SoundNet Flickr 144k | CIoU: 82.20 -> 82.80 | Improved |
| add IPL to dual teachers (ablation) | DMT · Flickr-SoundNet Flickr 144k | CIoU: 82.20 -> 83.60 | Improved |
| add filter to dual teachers (ablation) | DMT · Flickr-SoundNet Flickr 144k | CIoU: 82.20 -> 84.80 | Improved |
| add EMA on top of filter (ablation) | DMT · Flickr-SoundNet Flickr 144k | CIoU: 84.80 -> 86.20 | Improved |
| add IPL on top of filter (ablation) | DMT · Flickr-SoundNet Flickr 144k | CIoU: 84.80 -> 88.60 | Improved |
| add EMA on top of filter and IPL (ablation) | DMT · Flickr-SoundNet Flickr 144k | CIoU: 88.60 -> 90.40 | Improved |
| all three modules combined reduce MSE (ablation) | DMT · Flickr-SoundNet Flickr 144k | MSE: 0.382 -> 0.237 | Improved |
| increase labeled data from 256 to 4k | DMT · Flickr 10k | CIoU: 87.20 -> 88.80 | Improved |
| increase labeled data from 256 to 4k | DMT · VGG-Sound 144k | CIoU: 43.60 -> 48.80 | Improved |
| DMT vs naive SSL on attention10k | attention10k · open set | CIoU: 19.60 -> 42.64 | Improved |
Closest papers by meaning
- A Closer Look at Weakly-Supervised Audio-Visual Source Localization (NeurIPS 2022 · similarity 0.93)
- T-VSL: Text-Guided Visual Sound Source Localization in Mixtures (CVPR 2024 · similarity 0.90)
- Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer (AAAI 2024 · similarity 0.89)
- Object-aware Sound Source Localization via Audio-Visual Scene Understanding (CVPR 2025 · similarity 0.89)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.88)
- Improving Sound Source Localization with Joint Slot Attention on Image and Audio (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
