WaveMix: A Resource-efficient Neural Network for Image Analysis

arXiv:2205.14375v5 Announce Type: replace-cross
Abstract: We propose a novel neural architecture for computer vision -- WaveMix -- that is resource-efficient and yet generalizable and scalable. While using fewer trainable parameters, GPU RAM, and computations, WaveMix networks achieve comparable or better accuracy than the state-of-the-art convolutional neural networks, vision transformers, and token mixers for several tasks. This efficiency can translate to savings in time, cost, and energy. To achieve these gains we used multi-level two-dimensional discrete wavelet transform (2D-DWT) in WaveMix …

abstract accuracy analysis architecture art arxiv computer computer vision convolutional neural networks cs.ai cs.cv cs.lg gpu image network networks neural network neural networks novel parameters scalable state token transformers type vision vision transformers