Image/Document Clustering 벤치마크
Image/Document Clustering on pendigits
runtime (s) 낮을수록 좋음
- 2018-05-25 — SC_RB: runtime (s) 1.8
- 2019-03-04 — U-SPEC: runtime (s) 1.01
- 2021-04-30 — LSC-R: runtime (s) 0.77
- 2021-05-02 — DnC-SC: runtime (s) 0.64
| Rank | Model | runtime (s) | Accuracy (%) | NMI | Paper | Code | Year |
|---|---|---|---|---|---|---|---|
| 1 | DnC-SC | 0.64 | 82.27 | 82.86 | Divide-and-conquer based Large-Scale Spectral Clustering | Li-Hongmin/MyPaperWithCode | 2021 |
| 2 | LSC-R | 0.77 | 81.55 | 79.15 | Divide-and-conquer based Large-Scale Spectral Clustering | Li-Hongmin/MyPaperWithCode | 2021 |
| 3 | U-SPEC | 1.01 | – | 0.803 | Ultra-Scalable Spectral Clustering and Ensemble Clustering | 2019 | |
| 4 | LSC-K | 1.20 | 74.02 | 81.37 | Divide-and-conquer based Large-Scale Spectral Clustering | Li-Hongmin/MyPaperWithCode | 2021 |
| 5 | SC_RB | 1.8 | – | – | Scalable Spectral Clustering Using Random Binning Features | IBM/SpectralClustering_RandomBinning | 2018 |
| 6 | U-SPEC | 2.07 | 81.68 | 81.68 | Divide-and-conquer based Large-Scale Spectral Clustering | Li-Hongmin/MyPaperWithCode | 2021 |
| 7 | LBDM | 3.08 | 74.70 | – | Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs | 2018 |