Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
zjuter0126 4e762fe5f6 | 2 years ago | |
---|---|---|
.. | ||
callback.py | 2 years ago | |
config.py | 2 years ago | |
dataset.py | 2 years ago | |
lr_generator.py | 2 years ago | |
network.py | 2 years ago | |
resnet.py | 2 years ago |
细粒度分类具有挑战性,因为很难找到有区别的特征。找到那些能够完全描述物体的细微特征并不容易。为了解决这一问题,我们提出了一种新的自监督机制来有效地对信息区域进行定位,而不需要使用框/部件标注。我们的模型NTS-Net称为导航-教学-审查网络,由导航器代理、教学器代理和审查器代理组成。考虑到区域的信息量与其为groundtruth类的概率之间的内在一致性,设计了一种新的训练范式,使导航器能够在教学器的指导下检测出信息量最大的区域。然后,审查器从导航器中仔细识别建议的区域并做出预测。我们的模型可以看作是一个
Python Shell
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》