echoinside

This media is not supported in your browser

VIEW IN TELEGRAM

Explaining in Style: Training a GAN to explain a classifier in StyleSpace
[Google research]
* project page
* pdf
Image classification models can depend on multiple different semantic attributes of the image. An explanation of the decision of the classifier needs to both discover and visualize these properties. Here we present StylEx, a method for doing this, by training a generative model to specifically explain multiple attributes that underlie classifier decisions. We apply StylEx to multiple domains, including animals, leaves, faces and retinal images. For these, we show how an image can be modified in different ways to change its classifier output. Our results show that the method finds attributes that align well with semantic ones, generate meaningful image-specific explanations, and are human-interpretable as measured in user-studies.
#gan

www.tg-me.com/us/echoinside/com.echoinside/1868

180 viewsedited  Apr 28, 2021 at 08:58

Explaining in Style: Training a GAN to explain a classifier in StyleSpace
[Google research]
* project page
* pdf
Image classification models can depend on multiple different semantic attributes of the image. An explanation of the decision of the classifier needs to both discover and visualize these properties. Here we present StylEx, a method for doing this, by training a generative model to specifically explain multiple attributes that underlie classifier decisions. We apply StylEx to multiple domains, including animals, leaves, faces and retinal images. For these, we show how an image can be modified in different ways to change its classifier output. Our results show that the method finds attributes that align well with semantic ones, generate meaningful image-specific explanations, and are human-interpretable as measured in user-studies.
#gan

BY echoinside