AkiraTOSEI / ML_papers

ML_paper_summary(in Japanese)

5 stars 1 forks source link

The Origins and Prevalence of Texture Bias in Convolutional Neural Networks #131

Open AkiraTOSEI opened 3 years ago

AkiraTOSEI commented 3 years ago

TL;DR

Although it has been known that ImageNet-trained CNN models depend more on texture than on shape, they showed that using data augmentation methods,such as color-distortion, blur,can make the model classify objects based on shape. Table 1 Random-crop augmentation biases models towards texture Characteristics of ImageNet-

Why it matters:

Paper URL

https://arxiv.org/abs/1911.09071

Submission Dates(yyyy/mm/dd)

Authors and institutions

Methods

Results

Comments