Abstract | ||
---|---|---|
•Classical cross entropy loss may cause serious overfitting.•Regularization are beneficial to avoid overfitting.•Label distributions are more robust than hard labels. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.patrec.2022.02.011 | Pattern Recognition Letters |
Keywords | DocType | Volume |
Label Noise,Label Distribution,Semi-supervised Learning,Deep Learning | Journal | 155 |
ISSN | Citations | PageRank |
0167-8655 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Minxue Zhang | 1 | 0 | 0.34 |
xu ning | 2 | 25 | 15.72 |
Xin Geng | 3 | 1557 | 83.54 |