Timezone: »

 
Poster
CondConv: Conditionally Parameterized Convolutions for Efficient Inference
Brandon Yang · Gabriel Bender · Quoc V Le · Jiquan Ngiam

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #134
in Deep Learning -- CNN Architectures »

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. We demonstrate that scaling networks with CondConv improves the performance and inference cost trade-off of several existing convolutional neural network architectures on both classification and detection tasks. On ImageNet classification, our CondConv approach applied to EfficientNet-B0 achieves state-ofthe-art performance of 78.3% accuracy with only 413M multiply-adds. Code and checkpoints for the CondConv Tensorflow layer and CondConv-EfficientNet models are available at: https://github.com/tensorflow/tpu/tree/master/ models/official/efficientnet/condconv.

Keywords: Computer Vision · CNN Architectures · Applications · Deep Learning
[ Paper]  [ Poster] 

Author Information

Brandon Yang (Google Brain)
Gabriel Bender (Google Brain)
Quoc V Le (Google)
Jiquan Ngiam (Google Brain)

More from the Same Authors