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/DyMN-L

DyMN-L

Reported on 7 benchmarks across 3 tasks · 1 paper · 1 SOTA

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

Audio4 results

Instrument RecognitiononOpenMIC-2018
mean average precision· uses extra data· 2023-10-24
0.855
SOTA
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models arXiv:2310.15648
Audio ClassificationonESC-50
Accuracy (5-fold)· uses extra data· 2023-10-24
97.4
best: 99.1 (OmniVec2)
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models arXiv:2310.15648
Audio ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2023-10-24
97.4
best: 99.1 (OmniVec2)
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models arXiv:2310.15648
Audio ClassificationonFSD50K
mAP· uses extra data· 2023-10-24
65.5
best: 69.7 (ONE-PEACE)
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models arXiv:2310.15648

Methodology3 results

ClassificationonESC-50
Accuracy (5-fold)· uses extra data· 2023-10-24
97.4
best: 99.1 (OmniVec2)
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models arXiv:2310.15648
ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2023-10-24
97.4
best: 99.1 (OmniVec2)
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models arXiv:2310.15648
ClassificationonFSD50K
mAP· uses extra data· 2023-10-24
65.5
best: 69.7 (ONE-PEACE)
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models arXiv:2310.15648