Papers with Code · CC BY-SA 4.0

ESC-50

아카이브 평가 28건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
OmniVec2	Top-1 Accuracy 99.1 PRE-TRAINING DATASET Multiple Accuracy (5-fold) 99.1	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning 2024-01-01	연결 없음
InternVideo2	Top-1 Accuracy 98.6 PRE-TRAINING DATASET Multiple Accuracy (5-fold) 98.6	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding 2024-03-22	코드 1 · 코드 2
M2D2 AS+	Top-1 Accuracy 98.5 PRE-TRAINING DATASET AudioSet,WavCaps Accuracy (5-fold) 98.5	M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP 2025-03-28	코드 1 · 코드 2
OmniVec	Top-1 Accuracy 98.4 PRE-TRAINING DATASET Multiple Accuracy (5-fold) 98.4	OmniVec: Learning robust representations with cross modal sharing 2023-11-07	연결 없음
BEATs	Top-1 Accuracy 98.1 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 98.1	BEATs: Audio Pre-Training with Acoustic Tokenizers 2022-12-18	코드 1 · 코드 2 · 코드 3 · 코드 4
mn40_as	Top-1 Accuracy 97.45 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 97.45	Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation 2022-11-09	코드 1 · 코드 2
DyMN-L	Top-1 Accuracy 97.4 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 97.4	Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models 2023-10-24	코드 1
M2D-CLAP/0.7	Top-1 Accuracy 97.4 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 97.4	M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation 2024-06-04	코드 1 · 코드 2
M2D-AS/0.7	Top-1 Accuracy 97.2 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 97.2	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework 2024-04-09	코드 1 · 코드 2
HTS-AT	Top-1 Accuracy 97.0 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 97.0	HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection 2022-02-02	코드 1
EAT-M	Top-1 Accuracy 96.3 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 96.3	End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network 2022-04-25	코드 1
LHGNN	Top-1 Accuracy 96.2	LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging 2025-01-07	연결 없음
ERANN-2-5	Top-1 Accuracy 96.1 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 96.1	ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition 2021-06-03	연결 없음
M2D/0.7	Top-1 Accuracy 96.0 Accuracy (5-fold) 96.0	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework 2024-04-09	코드 1 · 코드 2
EAT	Top-1 Accuracy 96.0 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 96.0	EAT: Self-Supervised Pre-Training with Efficient Audio Transformer 2024-01-07	코드 1
Audio Spectrogram Transformer	Top-1 Accuracy 95.7 PRE-TRAINING DATASET AudioSet, ImageNet Accuracy (5-fold) 95.7	AST: Audio Spectrogram Transformer 2021-04-05	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
EAT-S	Top-1 Accuracy 95.25 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 95.25	End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network 2022-04-25	코드 1
MATPAC (SSL model, linear eval)	Top-1 Accuracy 93.5 PRE-TRAINING DATASET AudioSet Accuracy (5-fold) 93.5	Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning 2025-02-17	코드 1
EAT-S (scratch)	Top-1 Accuracy 92.15 Accuracy (5-fold) 92.15	End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network 2022-04-25	코드 1
SepTr + LeRaC	Top-1 Accuracy 91.58 Accuracy (5-fold) 91.58	Learning Rate Curriculum 2022-05-18	코드 1
SepTr	Top-1 Accuracy 91.13 PRE-TRAINING DATASET -	SepTr: Separable Transformer for Audio Spectrogram Processing 2022-03-17	코드 1
Multi-Format Contrastive	Top-1 Accuracy 90.5	Multi-Format Contrastive Learning of Audio Representations 2021-03-11	연결 없음
Multi-Channel Audio Feature with CNN	Top-1 Accuracy 89.5 PRE-TRAINING DATASET EfficientNet Accuracy (5-fold) 89.5	연결 없음 논문 날짜 미기재	연결 없음
AVID	Top-1 Accuracy 89.2	Audio-Visual Instance Discrimination with Cross-Modal Agreement 2020-04-27	코드 1
ACDNet	Top-1 Accuracy 87.1 Accuracy (5-fold) 87.1	Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices 2021-03-05	코드 1
XDC	Top-1 Accuracy 84.8 PRE-TRAINING DATASET AudioSet	Self-Supervised Learning by Cross-Modal Audio-Video Clustering 2019-11-28	코드 1
AVTS	Top-1 Accuracy 82.3	Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization 2018-06-30	연결 없음
L3	Top-1 Accuracy 79.3	Look, Listen and Learn 2017-05-23	코드 1