TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

SotA/Methodology/2D Classification/MUSDB18-HQ

2D Classification on MUSDB18-HQ

Metric: SDR (bass) (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕SDR (bass)▼AugmentationsPaperDate↕Code
1BS-RoFormer (L=12, OA)13.32Yes---
2BS-RoFormer (L=6, OA)11.31No---
3Sparse HT Demucs (fine tuned)10.47YesHybrid Transformers for Music Source Separation2022-11-15Code
4Hybrid Transformer Demucs (f.t.)10.39YesHybrid Transformers for Music Source Separation2022-11-15Code
5SCNet-large9.49NoSCNet: Sparse Compression Network for Music Sour...2024-01-24Code
6SCNet8.82NoSCNet: Sparse Compression Network for Music Sour...2024-01-24Code
7Hybrid Demucs8.76NoHybrid Spectrogram and Waveform Source Separation2021-11-05Code
8TFC-TDF-UNet (v3)8.45NoSound Demixing Challenge 2023 Music Demixing Tra...2023-06-15Code
9Band-Split RNN (semi-sup.)8.16YesMusic Source Separation with Band-split RNN2022-09-30Code
10KUIELab-MDX-Net7.83NoKUIELab-MDX-Net: A Two-Stream Neural Network for...2021-11-24Code
11Dual-Path TFC-TDF UNet (DTTNet)7.55NoMusic Source Separation Based on a Lightweight D...2023-09-15Code
12Band-Split RNN7.22NoMusic Source Separation with Band-split RNN2022-09-30Code
13CWS-PResUNet5.93NoCWS-PResUNet: Music Source Separation with Chann...2021-12-09Code
14Unmix4.073NoTransfer Learning with Jukebox for Music Source ...2021-11-28Code