Papers with Code · CC BY-SA 4.0

AudioSet

아카이브 평가 51건 · 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	Test mAP 0.558	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning 2024-01-01	연결 없음
OmniVec	Test mAP 0.548	OmniVec: Learning robust representations with cross modal sharing 2023-11-07	연결 없음
EquiAV	Test mAP 0.546	EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning 2024-03-14	코드 1
MAViL (Audio-Visual, single)	Test mAP 0.533	연결 없음 논문 날짜 미기재	연결 없음
Audiovisual Masked Autoencoder (Audiovisual, Single)	Test mAP 0.518	Audiovisual Masked Autoencoders 2022-12-09	코드 1 · 코드 2
CAV-MAE (Audio-Visual)	Test mAP 0.512	Contrastive Audio-Visual Masked Autoencoder 2022-10-02	코드 1
BEATs (Audio-only, Ensemble)	Test mAP 0.506	BEATs: Audio Pre-Training with Acoustic Tokenizers 2022-12-18	코드 1 · 코드 2 · 코드 3 · 코드 4
UAVM (Audio + Video)	Test mAP 0.504	UAVM: Towards Unifying Audio and Visual Models 2022-07-29	코드 1
SSLAM (Audio-Only, Single)	Test mAP 0.502	SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes 2025-06-13	코드 1
mn40_as (Ensemble)	Test mAP 0.498	Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation 2022-11-09	코드 1 · 코드 2
ATST-C2F(Single)	Test mAP 0.497	Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks 2023-06-07	코드 1 · 코드 2
MBT (AS-500K training + Video)	Test mAP 0.496	Attention Bottlenecks for Multimodal Fusion 2021-06-30	코드 1
PaSST (Ensemble)	Test mAP 0.496	Efficient Training of Audio Transformers with Patchout 2021-10-11	코드 1 · 코드 2
DyMN-L (Audio-Only, Single)	Test mAP 0.490	Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models 2023-10-24	코드 1
M2D2	Test mAP 0.490	M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP 2025-03-28	코드 1 · 코드 2
HTS-AT (Ensemble)	Test mAP 0.487	HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection 2022-02-02	코드 1
BEATs (Audio-only, Single)	Test mAP 0.486	BEATs: Audio Pre-Training with Acoustic Tokenizers 2022-12-18	코드 1 · 코드 2 · 코드 3 · 코드 4
EAT	Test mAP 0.486	EAT: Self-Supervised Pre-Training with Efficient Audio Transformer 2024-01-07	코드 1
DTF-AT (Single)	Test mAP 0.486	DTF-AT: Decoupled Time-Frequency Audio Transformer for Event Classification 2024-03-24	코드 1
AST (Ensemble)	Test mAP 0.485	AST: Audio Spectrogram Transformer 2021-04-05	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
M2D-CLAP/0.7	Test mAP 0.485	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	Test mAP 0.485	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework 2024-04-09	코드 1 · 코드 2
MAViL (Audio-only, single)	Test mAP 0.484	연결 없음 논문 날짜 미기재	연결 없음
mn40_as (Single)	Test mAP 0.483	Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation 2022-11-09	코드 1 · 코드 2
MAX-AST (Single)	Test mAP 0.481	MAX-AST: COMBINING CONVOLUTION, LOCAL AND GLOBAL SELF-ATTENTIONS FOR AUDIO EVENT CLASSIFICATION 2024-04-14	코드 1
ATST-Frame	Test mAP 0.480	Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks 2023-06-07	코드 1 · 코드 2
M2D/0.7	Test mAP 0.479	Masked Modeling Duo: Towards a Universal Audio Pre-training Framework 2024-04-09	코드 1 · 코드 2
PlayItBackX3	Test mAP 0.477	Play It Back: Iterative Attention for Audio Recognition 2022-10-20	코드 1
DASS-Medium (Audio-only, single)	Test mAP 0.476	DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable Learners 2024-07-04	코드 1
PSLA (Ensemble)	Test mAP 0.474 AUC 0.981 d-prime 2.936	PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation 2021-02-02	코드 1