Open wangjing60755 opened 1 month ago
In semantic perception tasks, there is less experience to refer to. However, for classification, there are many self-training methods available. One notable reference is the "End-to-End Semi-Supervised Object Detection with Soft Teacher" for object detection.
代码中的weak_aug采用flip,strong_aug采用色彩增强,这个操作有啥理论支撑吗?在各数据集中都是有效的吗?
我的数据对颜色比较敏感,在监督训练中使用色彩增强效果较差。
对于色彩敏感的任务,strong_aug应该怎么设置?是否有可分享的经验?
感谢!