HyperAI超神経

プラットフォーム

Audio Classification On Balanced Audio Set

評価指標

Mean AP

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title
EquiAV	42.4	EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
SSLAM	40.9	SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes
EAT	40.3	EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
BEATs	38.9	BEATs: Audio Pre-Training with Acoustic Tokenizers
Base (ours)	37.4	ATST: Audio Representation Learning with Teacher-Student Transformer
SSAST-PATCH	31.0	SSAST: Self-Supervised Audio Spectrogram Transformer
SSAST-FRAME	29.2	SSAST: Self-Supervised Audio Spectrogram Transformer
Conformer	27.6	Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks

0 of 8 row(s) selected.

Audio Classification On Balanced Audio Set | SOTA | HyperAI超神経