Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/M2D-AS/0.7

M2D-AS/0.7

Reported on 8 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio4 results

Audio ClassificationonAudio Set
Mean AP· 2024-04-09
48.5
SOTA
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework arXiv:2404.06095
Audio ClassificationonESC-50
Accuracy (5-fold)· uses extra data· 2024-04-09
97.2
best: 99.1 (OmniVec2)
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework arXiv:2404.06095
Audio ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2024-04-09
97.2
best: 99.1 (OmniVec2)
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework arXiv:2404.06095
Audio ClassificationonAudioSet
Test mAP· 2024-04-09
0.485
best: 0.558 (OmniVec2)
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework arXiv:2404.06095

Methodology4 results

ClassificationonAudio Set
Mean AP· 2024-04-09
48.5
SOTA
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework arXiv:2404.06095
ClassificationonESC-50
Accuracy (5-fold)· uses extra data· 2024-04-09
97.2
best: 99.1 (OmniVec2)
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework arXiv:2404.06095
ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2024-04-09
97.2
best: 99.1 (OmniVec2)
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework arXiv:2404.06095
ClassificationonAudioSet
Test mAP· 2024-04-09
0.485
best: 0.558 (OmniVec2)
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework arXiv:2404.06095