We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
作者,你好,很棒的工作。想问下作者有没有尝试过通过计算标签(groundtruth)的位置关系得到先验位置关系设计位置编码器呢。
No response
The text was updated successfully, but these errors were encountered:
我并没有尝试过这种思路,感觉预先统计的先验可能更倾向于反应“平均”后的关系,但不能灵活地反应样本间的方差。 但确实有这么做的论文,比如在我related work中有提到,有的方法会从Visual Genome数据库中挑选出所需要的类别来统计各种先验关系,然后固定下来作为一个全局的特征或网络参数,这个数据库有很多relation标注。小样本学习中也有类似的做法,他们会用预训练的网络(比如ResNet)提取每个类别的平均特征,然后把这些特征固定下来作为网络参数,用来和后续的输入样本做交互。 但是总体来说,我觉得这个思路更适用于同类别样本方差较小或者样本较少的情况,这样预先提取的先验才足够代表大部分样本,比如长尾分布或者小样本任务。
Sorry, something went wrong.
No branches or pull requests
Question
作者,你好,很棒的工作。想问下作者有没有尝试过通过计算标签(groundtruth)的位置关系得到先验位置关系设计位置编码器呢。
补充信息
No response
The text was updated successfully, but these errors were encountered: