Audio Classification On Esc 50

评估指标

Top-1 Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
OmniVec2	99.1	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning	-
InternVideo2	98.6	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
OmniVec	98.4	OmniVec: Learning robust representations with cross modal sharing	-
BEATs	98.1	BEATs: Audio Pre-Training with Acoustic Tokenizers
mn40_as	97.45	Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation
M2D-CLAP/0.7	97.4	M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation
DyMN-L	97.4	Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models
M2D-AS/0.7	97.2	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework
HTS-AT	97.0	HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection
EAT-M	96.3	End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network
LHGNN	96.2	LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging	-
ERANN-2-5	96.1	ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition	-
M2D/0.7	96.0	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework
EAT	96.0	EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
Audio Spectrogram Transformer	95.7	AST: Audio Spectrogram Transformer
EAT-S	95.25	End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network
EAT-S (scratch)	92.15	End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network
SepTr + LeRaC	91.58	Learning Rate Curriculum
SepTr	91.13	SepTr: Separable Transformer for Audio Spectrogram Processing
Multi-Format Contrastive	90.5	Multi-Format Contrastive Learning of Audio Representations	-

0 of 27 row(s) selected.