Open AkiraTOSEI opened 3 years ago
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.
https://arxiv.org/abs/1911.09071
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-](https://user-images.githubusercontent.com/24524018/95158854-9d19aa00-07d7-11eb-9718-55dbe5006052.png)
Why it matters:
Paper URL
https://arxiv.org/abs/1911.09071
Submission Dates(yyyy/mm/dd)
Authors and institutions
Methods
Results
Comments