EffNet: An Efficient Structure for Convolutional Neural Networks
This work addresses the need for efficient neural networks for customer products on mobile hardware, representing an incremental improvement over existing slim models.
The authors tackled the problem of running convolutional neural networks efficiently on embedded and mobile hardware by proposing a novel convolution block, EffNet, which reduces computational burden and surpasses current state-of-the-art models like MobileNet and ShuffleNet.
With the ever increasing application of Convolutional Neural Networks to customer products the need emerges for models to efficiently run on embedded, mobile hardware. Slimmer models have therefore become a hot research topic with various approaches which vary from binary networks to revised convolution layers. We offer our contribution to the latter and propose a novel convolution block which significantly reduces the computational burden while surpassing the current state-of-the-art. Our model, dubbed EffNet, is optimised for models which are slim to begin with and is created to tackle issues in existing models such as MobileNet and ShuffleNet.