本文主要是介绍Learning Integral Objects with Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!
When the number of class is n, the number of this method is 2n. As the photo show. Every class separated to foreground and background.
Q1: The ‘C’ on this photo means the number of class? If do, why it must be it?
Q2: As w is a vector, is f a c dimensional vector?
The theory is the value of foreground and background is distinguished on feature map. ‘w’ can transform feature vector of each pixel to a score represent binary class. We name this score S.
S ′ S' S′ just make fg part to positive and bg to negative.
S ′ ′ S'' S′′ were learnt by optimize followed equation.
where S ′ ′ S'' S′′ is the final score
这篇关于Learning Integral Objects with Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!