AI Paper Atlas

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

AAAI 2021 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning · 15 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use multi- to single-modal mutual learning instead of standard back-propagationAudio tagging student network · DCASE17mAP: 0.5918 -> 0.6421Improved
Use multi- to single-modal mutual learning instead of standard back-propagationAudio tagging student network · DCASE18mAP: 0.8637 -> 0.8855Improved
Add VGGish acoustic representations to the mutual-learning studentProposed student network · DCASE17mAP: 0.6366 -> 0.6690Improved
Add VGGish acoustic representations to the mutual-learning studentProposed student network · DCASE18mAP: 0.8845 -> 0.9059Improved
Use VGG-4096 rather than VGG-1000 visual featuresAudio tagging feature model · DCASE17mAP: 0.4512 -> 0.5225Improved
Use VGG-4096 rather than VGG-1000 visual featuresAudio tagging feature model · DCASE18mAP: 0.6930 -> 0.7750Improved
Add mutual learning between teacher and student (ablation)Proposed student network · DCASE17mAP: 0.6359 -> 0.6421; -1.0%Improved
Add mutual learning between teacher and student (ablation)Proposed student network · DCASE18mAP: 0.8760 -> 0.8855; -1.1%Improved
Add single-modal transfer loss (ablation)Proposed student network · DCASE17mAP: 0.6317 -> 0.6421; -1.6%Improved
Add single-modal transfer loss (ablation)Proposed student network · DCASE18mAP: 0.8702 -> 0.8855; -1.7%Improved
Add cross-modal transfer loss (ablation)Proposed student network · DCASE17mAP: 0.6353 -> 0.6421; -1.1%Improved
Add cross-modal transfer loss (ablation)Proposed student network · DCASE18mAP: 0.8775 -> 0.8855; -0.9%Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy