研究文章
异常检测与改善Autoencoder大数据集
|
| 方法 |
大道 |
ShanghaiTech |
|
| MPPCA +科幻 |
56.2% |
- - - - - - |
| 联合化疗 |
77.4% |
- - - - - - |
| Conv-AE |
80.0% |
60.9% |
| Conv3D-AE |
80.9% |
- - - - - - |
| 堆叠RNN |
81.7% |
68.0% |
| ConvLSTM-AE |
77.0% |
- - - - - - |
| MemNormality |
88.5% |
70.5% |
| ClusterAE |
86.0% |
73.3% |
| AbnormalGAN |
- - - - - - |
72.4% |
| Pred +侦察 |
85.1% |
73.0% |
| 该方法 |
85.9% |
75.4% |
|
|
