一种基于少样本数据的在线主动学习与分类方法
|
|
杨静, 赵文仓, 徐越, 冯旸赫, 黄金才
|
An on⁃line active learning and classification method based on small sample data
|
|
Jing Yang, Wencang Zhao, Yue Xu, Yanghe Feng, Jincai Huang
|
|
表3 CIFAR?100的识别结果
|
Table 3 Recognition result for CIFAR?100 dataset
|
|
| 方法 | T9 | T16 | T23 | T30 | T44 | T51 | T58 | T65 | T72 | T79 | T86 | T93 | T100 |
|---|
| 变异比 | 19.03% | 23.14% | 23.29% | 24.44% | 27.60% | 27.97% | 29.89% | 30.97% | 32.98% | 32.86% | 33.84% | 34.19% | 35.15% | | 预测熵 | 21.13% | 23.24% | 26.13% | 27.52% | 30.04% | 30.80% | 32.34% | 33.10% | 33.05% | 34.53% | 35.46% | 35.62% | 36.58% | | BALD | 23.26% | 25.96% | 27.77% | 29.29% | 31.26% | 31.50% | 33.01% | 33.84% | 34.83% | 35.69% | 36.16% | 35.79% | 37.81% | | CISs | 28.81% | 31.06% | 32.23% | 33.22% | 35.01% | 36.26% | 37.04% | 37.72% | 39.16% | 39.24% | 40.18% | 38.65% | 40.18% |
|
|
|