Research map / Vision-language and multimodal / Cross-modal learning
Enhanced Audio Tagging via Multi- to Single-Modal Teacher-Student Mutual Learning
Yifang Yin, Harsh Shrivastava, Ying Zhang, Zhenguang Liu, Rajiv Ratn Shah, Roger Zimmermann
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 multi- to single-modal mutual learning instead of standard back-propagation | Audio tagging student network · DCASE17 | mAP: 0.5918 -> 0.6421 | Improved |
| Use multi- to single-modal mutual learning instead of standard back-propagation | Audio tagging student network · DCASE18 | mAP: 0.8637 -> 0.8855 | Improved |
| Add VGGish acoustic representations to the mutual-learning student | Proposed student network · DCASE17 | mAP: 0.6366 -> 0.6690 | Improved |
| Add VGGish acoustic representations to the mutual-learning student | Proposed student network · DCASE18 | mAP: 0.8845 -> 0.9059 | Improved |
| Use VGG-4096 rather than VGG-1000 visual features | Audio tagging feature model · DCASE17 | mAP: 0.4512 -> 0.5225 | Improved |
| Use VGG-4096 rather than VGG-1000 visual features | Audio tagging feature model · DCASE18 | mAP: 0.6930 -> 0.7750 | Improved |
| Add mutual learning between teacher and student (ablation) | Proposed student network · DCASE17 | mAP: 0.6359 -> 0.6421; -1.0% | Improved |
| Add mutual learning between teacher and student (ablation) | Proposed student network · DCASE18 | mAP: 0.8760 -> 0.8855; -1.1% | Improved |
| Add single-modal transfer loss (ablation) | Proposed student network · DCASE17 | mAP: 0.6317 -> 0.6421; -1.6% | Improved |
| Add single-modal transfer loss (ablation) | Proposed student network · DCASE18 | mAP: 0.8702 -> 0.8855; -1.7% | Improved |
| Add cross-modal transfer loss (ablation) | Proposed student network · DCASE17 | mAP: 0.6353 -> 0.6421; -1.1% | Improved |
| Add cross-modal transfer loss (ablation) | Proposed student network · DCASE18 | mAP: 0.8775 -> 0.8855; -0.9% | Improved |
Closest papers by meaning
- Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser (NeurIPS 2023 · similarity 0.89)
- Enhancing Audio-Visual Association with Self-Supervised Curriculum Learning (AAAI 2021 · similarity 0.88)
- CoLeaF: A Contrastive-Collaborative Learning Framework for Weakly Supervised Audio-Visual Video Parsing (ECCV 2024 · similarity 0.88)
- Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing (AAAI 2025 · similarity 0.85)
- Audio-Visual Semantic Graph Network for Audio-Visual Event Localization (CVPR 2025 · similarity 0.85)
- Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds (CVPR 2025 · similarity 0.85)
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.
