VGG - computing cam and use of sqrt

jiwoon-ahn / psa

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

MIT License

380 stars 62 forks source link

Open saurabheights-ecr opened 3 years ago

saurabheights-ecr commented 3 years ago

At line https://github.com/jiwoon-ahn/psa/blob/master/network/vgg16_cls.py#L36. CAM is weighted combination of feature maps, so not sure why sqrt is used.

Please, could you provide some clarification.

Zhengyang1995 commented 2 years ago

I also want to know the answer for it, thanks