Open liubaoning111 opened 2 weeks ago
In cases with only one target in an image, the absence of negative samples in the contrast loss construction results in a constant 0 loss. We have used a method to treat the background as a special instance. We will update the new version to avoid this problem soon.
你好,我想问下,咱们的弱监督是可以分割多个目标的吗?我有一个msk有四个目标,背景0,目标1:1,目标2:2,目标3:3,可以直接实现分割吗?
可以的,SAM原本支持什么样的分割,我们也同样支持。弱监督的格式是SAM接收的prompt格式。
我的也是,但不是对比损失