Audio Classification On Audioset

Metrics

Test mAP

Results

Performance results of various models on this benchmark

Model Name	Test mAP	Paper Title	Repository
EAT	0.486	EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
mn40_as (Single)	0.483	Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation
M2D-AS/0.7	0.485	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework
MAViL (Audio-Visual, single)	0.533	-	-
EAT-S	0.405	End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network
BEATs (Audio-only, Single)	0.486	BEATs: Audio Pre-Training with Acoustic Tokenizers
CAV-MAE (Audio-Visual)	0.512	Contrastive Audio-Visual Masked Autoencoder
L3	0.249	Look, Listen and Learn
OmniVec2	0.558	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning	-
PSLA (Single)	0.443	PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation
EAT-M	0.426	End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network
ATST-Frame	0.480	Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks
CAV-MAE (Audio-Only)	0.466	Contrastive Audio-Visual Masked Autoencoder
DTF-AT (Single)	0.486	DTF-AT: Decoupled Time-Frequency Audio Transformer for Event Classification
Audiovisual Masked Autoencoder (Audio-only, Single)	0.466	Audiovisual Masked Autoencoders
AST (Ensemble)	0.485	AST: Audio Spectrogram Transformer
BEATs (Audio-only, Ensemble)	0.506	BEATs: Audio Pre-Training with Acoustic Tokenizers
EquiAV	0.546	EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
MMV	0.309	Self-Supervised MultiModal Versatile Networks
CAV-MAE (Visual-Only)	0.262	Contrastive Audio-Visual Masked Autoencoder

0 of 50 row(s) selected.