Label Distribution Learning on SCUT (3 random splits)
0.2949KL DivergenceERDF
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| ERDFnumber of trees=100, max depth=10, max cascade forest layers=10, early stopping tolerance=1, feature enhancement k=52026.02 | 0.2949 | 0.2092 | 1.3523 | 2.4651 | 0.8782 | 75.52 | |
| StructRFnumber of trees=100, max depth=102026.02 | 0.3337 | 0.2303 | 1.3675 | 2.522 | 0.8624 | 72.1 | |
| AA-BPoptimizer=SA-BFGS, max iterations=5002026.02 | 0.3851 | 0.2629 | 1.3846 | 2.5792 | 0.8414 | 67.92 | |
| AA-KNNk=5, distance metric=minkowski2026.02 | 0.5241 | 0.2537 | 1.3043 | 2.3985 | 0.8294 | 69.42 | |
| LDL-SCLhyperparameters=λ1, λ2, λ3 tuned from {10^-1, 10^-2, 10^-3}, number of clusters=5 or 102026.02 | 0.5647 | 0.3418 | 1.4561 | 2.8076 | 0.7598 | 57.5 |