A Push-Pull Layer Improves Robustness of Convolutional Neural Networks

We propose a new layer in Convolutional Neural Networks (CNNs) to increase their robustness to several types of noise perturbations of the input images. We call this a push-pull layer and compute its response as the combination of two half-wave rectified convolutions, with kernels of opposite polarity... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
Convolution
Convolutions
Dropout
Regularization
Batch Normalization
Normalization
Global Average Pooling
Pooling Operations
Residual Connection
Skip Connections
ReLU
Activation Functions
Kaiming Initialization
Initialization
Wide Residual Block
Skip Connection Blocks
WideResNet
Image Models