Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

我的一些理解 #21

Open
jinweiisgreat opened this issue May 5, 2023 · 1 comment
Open

我的一些理解 #21

jinweiisgreat opened this issue May 5, 2023 · 1 comment

Comments

@jinweiisgreat
Copy link

说一下我的理解和问题:

  1. 做不了细分类的原因是,训练阶段的mini-batch是只获取IoU0.5以上的框,目的就是对已知instance建模。因此整个模型就没有考虑到unknown instance。只是在test的时候,或者说,相当于后处理方法,给目标一个分数来判断是否是已知或者未知,这也是为什么文中会说:“Furthermore, since background proposals usually overwhelm the mini-batch, we sample the same number of foreground and background proposals, enabling our model to recall unknown objects from the background class.”
  2. 我的问题是,我在 只找到正样本部分,没找到处理负样本的代码。这虽然会让正样本类会更近,但并不会让不同类的样本更远呀?
    希望得到回复!谢谢
@csuhan
Copy link
Owner

csuhan commented May 6, 2023

  1. 是的。模型只能找到和foreground相似的unknown
  2. 正样本:known classes。负样本:background。在known classes + background之间计算contrastive loss会让不同类更远的。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants