Hyper-Convolutions via Implicit Kernels for Medical Imaging

Autor:	Ma, Tianyu, Wang, Alan Q., Dalca, Adrian V., Sabuncu, Mert R.
Rok vydání:	2022
Předmět:	Electrical Engineering and Systems Science - Image and Video Processing Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	The convolutional neural network (CNN) is one of the most commonly used architectures for computer vision tasks. The key building block of a CNN is the convolutional kernel that aggregates information from the pixel neighborhood and shares weights across all pixels. A standard CNN's capacity, and thus its performance, is directly related to the number of learnable kernel weights, which is determined by the number of channels and the kernel size (support). In this paper, we present the \textit{hyper-convolution}, a novel building block that implicitly encodes the convolutional kernel using spatial coordinates. Hyper-convolutions decouple kernel size from the total number of learnable parameters, enabling a more flexible architecture design. We demonstrate in our experiments that replacing regular convolutions with hyper-convolutions can improve performance with less parameters, and increase robustness against noise. We provide our code here: \emph{https://github.com/tym002/Hyper-Convolution} Comment: arXiv admin note: substantial text overlap with arXiv:2105.10559
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2202.02701 Zobrazit plný text záznamu View this record from Arxiv