Audio Classification On Audioset

评估指标

Test mAP

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
OmniVec2	0.558	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning	-
OmniVec	0.548	OmniVec: Learning robust representations with cross modal sharing	-
EquiAV	0.546	EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
MAViL (Audio-Visual, single)	0.533	-	-
Audiovisual Masked Autoencoder (Audiovisual, Single)	0.518	Audiovisual Masked Autoencoders
CAV-MAE (Audio-Visual)	0.512	Contrastive Audio-Visual Masked Autoencoder
BEATs (Audio-only, Ensemble)	0.506	BEATs: Audio Pre-Training with Acoustic Tokenizers
UAVM (Audio + Video)	0.504	UAVM: Towards Unifying Audio and Visual Models
SSLAM (Audio-Only, Single)	0.502	SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes	-
mn40_as (Ensemble)	0.498	Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation
ATST-C2F(Single)	0.497	Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks
MBT (AS-500K training + Video)	0.496	Attention Bottlenecks for Multimodal Fusion
PaSST (Ensemble)	0.496	Efficient Training of Audio Transformers with Patchout
DyMN-L (Audio-Only, Single)	0.490	Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models
HTS-AT (Ensemble)	0.487	HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection
EAT	0.486	EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
BEATs (Audio-only, Single)	0.486	BEATs: Audio Pre-Training with Acoustic Tokenizers
DTF-AT (Single)	0.486	DTF-AT: Decoupled Time-Frequency Audio Transformer for Event Classification	-
M2D-AS/0.7	0.485	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework
AST (Ensemble)	0.485	AST: Audio Spectrogram Transformer

0 of 50 row(s) selected.