Boost neural network performance with circular kernels instead of square ones
Boost neural network performance with circular kernels instead of square ones
Integrating Circle Kernels into Convolutional Neural Networks
arXiv paper abstract https://arxiv.org/abs/2107.02451v2
arXiv PDF paper https://arxiv.org/pdf/2107.02451v2.pdf
The square kernel is a standard unit for contemporary Convolutional Neural Networks (CNNs)
… However, the receptive field in the human … is … like a circle.
… propose using circle kernels with isotropic receptive fields for the convolution, and our training takes approximately equivalent amount of calculation
… reparameterize … thus taking no extra computation as well as the number of parameter overhead for the testing.
… approach exhibits highly competitive performance.
… ImageNet with standard data augmentation, our approach dramatically boosts the performance of MobileNetV3-Small by 5.20% top-1 accuracy and 3.39% top-5 accuracy, and boosts the performance of MobileNetV3-Large by 2.16% top-1 accuracy and 1.18% top-5 accuracy.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
