《Table 2 F1 score for each class, for each method》
提示：宽带有限、当前游客访问压缩模式
本系列图表出处文件名：随高清版一同展现
《Transferring pose and augmenting background for deep human-image parsing and its applications》
When transferring pose estimation information to the human-image parsing part，the performance improved for both 1000 and 6000 training images.Furthermore，as shown in Table 2，a similar tendency was confirmed for F1 for each class.In particular，with few training images，our data augmentation method outperformed the baseline for multiple classes，including the background（bg）class.Even when many training images were used，the proposed network based on pose estimation significantly outperformed the baseline for all labels except scarf.
| 图表编号 | XD0013092700 严禁用于非法目的 |
|---|---|
| 绘制时间 | 2018.03.01 |
| 作者 | Takazumi Kikuchi、Yuki Endo、Yoshihiro Kanamori、Taisuke Hashimoto、Jun Mitani |
| 绘制单位 | University of Tsukuba、University of Tsukuba、University of Tsukuba、University of Tsukuba、University of Tsukuba |
| 更多格式 | 高清、无水印（增值服务） |
