CondConv: Conditionally Parameterized Convolutions for Efficient Inference

Understand

Convolutional layers are one of the basic building blocks of modern deep neural networks.

• One fundamental assumption is that convolutional kernels should be shared for all examples in a dataset.
• We propose conditionally parameterized convolutions (CondConv), which learn specialized convolutional kernels for each example.
• Replacing normal convolutions with CondConv enables us to increase the size and capacity of a network, while maintaining efficient inference.