Scaling Up Computer Vision Neural Networks Using Fast Fourier Transform

Autor:	Agrawal, Siddharth
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Deep Learning-based Computer Vision field has recently been trying to explore larger kernels for convolution to effectively scale up Convolutional Neural Networks. Simultaneously, new paradigm of models such as Vision Transformers find it difficult to scale up to larger higher resolution images due to their quadratic complexity in terms of input sequence. In this report, Fast Fourier Transform is utilised in various ways to provide some solutions to these issues.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2302.12185 Zobrazit plný text záznamu View this record from Arxiv