wpy1999/bas

[CVPR2022] PyTorch implementation of ''Background Activation Suppression for Weakly Supervised Object Localization''.

bas's Issues

cannot reproduce the result in the essay

Your work is really great. I have trained a new vgg16 model based on your public code and default parameters. However, my test result is smaller than the result in the essay. I have tried change the batch size to 64, the result is improved but still smaller than the result in the essay. I wonder whether the default parameters are right and what is the batch size of the vgg16. I'll appreciate it if you can help me figure out my problem, thanks

goooooood job！

code for visualization

Hello！Could you provide the code for visual experimental results(activation map and bbox)?

bas seems not to work

Great work!
I have tried to reproduce the paper. Experiment reaches expectation on baseline(using foreground, AC and CLS loss). However, after adding the BAS loss, regression drops to 0. I have tried various version of BAS including detach background map and so on. Also the description does not match with the demo graph. Could you please share some details of how to train with BAS Loss. Thanks

关于LOSSac

您好！关于您的论文有个小问题：
请问您Area Constraint Loss在代码中哪一部分？我没有找到这个

非常感谢您优秀的工作！