Name
Title | ||
|---|---|---|
Early prediction for mode anomaly in generative adversarial network training: An empirical study. |
Abstract | ||
|---|---|---|
•A first study that targets at the early prediction of mode anomaly within GANs is presented.•With comparison to GAN related metrics, we find the early prediction for mode anomaly within GANs is feasible.•Three fine-grained metrics for the anomaly prediction is proposed.•A prediction strategy based on the anomaly signs is proposed and corresponding framework is built.•The prediction is demonstrated to be more effective than human perception. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.ins.2020.05.046 | Information Sciences |
Keywords | DocType | Volume |
Mode collapse,Mode dropping,Generative adversarial network,Metrics,Prediction | Journal | 534 |
ISSN | Citations | PageRank |
0020-0255 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chenkai Guo | 1 | 6 | 5.48 |
| Dengrong Huang | 2 | 0 | 1.69 |
| Jianwen Zhang | 3 | 319 | 14.74 |
| Xu Jing | 4 | 9 | 6.01 |
| Guangdong Bai | 5 | 10 | 4.90 |
| Naipeng Dong | 6 | 1 | 2.38 |