Audio Classification on ESC-50

59개 결과 · ⬇ CSV · JSON

Top-1 Accuracy

Rank	Model	Top-1 Accuracy	PRE-TRAINING DATASET	Accuracy (5-fold)	Extra Training Data	Paper	Code	Year
21	SepTr	91.13	-	–		SepTr: Separable Transformer for Audio Spectrogram Processing	ristea/septr	2022
22	Multi-Format Contrastive	90.5	–	–	✓	Multi-Format Contrastive Learning of Audio Representations		2021
23	Multi-Channel Audio Feature with CNN	89.5	EfficientNet	89.5
24	AVID	89.2	–	–		Audio-Visual Instance Discrimination with Cross-Modal Agreement	facebookresearch/AVID-CMA	2020
25	ACDNet	87.1	–	87.1		Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices	mohaimenz/acdnet	2021
26	XDC	85.4	IG-Random	–		Self-Supervised Learning by Cross-Modal Audio-Video Clustering	HumamAlwassel/XDC	2019
27	XDC	84.8	AudioSet	–		Self-Supervised Learning by Cross-Modal Audio-Video Clustering	HumamAlwassel/XDC	2019
28	AVTS	82.3	–	–		Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization		2018
29	L3	79.3	–	–		Look, Listen and Learn	marl/l3embedding	2017
30	OmniVec2	99.1	Multiple	99.1	✓	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning		2024
31	InternVideo2	98.6	Multiple	98.6	✓	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding	opengvlab/internvideo · opengvlab/internvideo2	2024
32	M2D2 AS+	98.5	AudioSet,WavCaps	98.5	✓	M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP	nttcslab/m2d · nttcslab/eval-audio-repr	2025
33	OmniVec	98.4	Multiple	98.4	✓	OmniVec: Learning robust representations with cross modal sharing		2023
34	BEATs	98.1	AudioSet	98.1	✓	BEATs: Audio Pre-Training with Acoustic Tokenizers	microsoft/unilm · Yui010206/CREMA · qingyuliu0521/icsd · +1	2022
35	mn40_as	97.45	AudioSet	97.45	✓	Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation	fschmid56/efficientat · fschmid56/efficientat_hear	2022
36	DyMN-L	97.4	AudioSet	97.4	✓	Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models	fschmid56/efficientat	2023
36	M2D-CLAP/0.7	97.4	AudioSet	97.4	✓	M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation	nttcslab/m2d · nttcslab/eval-audio-repr	2024
38	M2D-AS/0.7	97.2	AudioSet	97.2	✓	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework	nttcslab/m2d · nttcslab/eval-audio-repr	2024
39	HTS-AT	97.0	AudioSet	97.0	✓	HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection	retrocirce/hts-audio-transformer	2022
40	EAT-M	96.3	AudioSet	96.3	✓	End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network	Alibaba-MIIL/AudioClassfication	2022