DFT-based Transformation Invariant Pooling Layer for Visual Classification
ECCV, pp. 89-104, 2018.
When the network does not have an average pooling layer, e.g., AlexNet and VGG, the DFT magnitude pooling is inserted between the final convolution and first fully-connected layers
We propose a novel discrete Fourier transform-based pooling layer for convolutional neural networks. The DFT magnitude pooling replaces the traditional max/average pooling layer between the convolution and fully-connected layers to retain translation invariance and shape preserving (aware of shape difference) properties based on the shift...More
PPT (Upload PPT)