CondConv: Conditionally Parameterized Convolutions for Efficient Inference

NeurIPS 2019 Brandon YangGabriel BenderQuoc V. LeJiquan Ngiam

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... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Image Classification ImageNet EfficientNet-B0 (CondConv) Top 1 Accuracy 78.3% # 66