Why can it get rich convolution features?

yun-liu / RCF

Richer Convolutional Features for Edge Detection

Other

753 stars 259 forks source link

Why can it get rich convolution features? #59

Closed InstantWindy closed 5 years ago

InstantWindy commented 5 years ago

Hello! I wonder why richer convolution can be obtained by adding 1x1 convolution after 3x3 convolution? Thank you !

frankie-yanfeng commented 5 years ago

@yun-liu I guess this is not where richer convolution feature is from. The introduced 1x1 conv after 3x3 is used to decrease the channel and organize the feature map. After eltwise layer, they are somehow added together, which could be visualized as hyper-column.