Shypd.aiThe largest open index of AI toolsGFNet is an AI tool for image classification that utilizes Global Filter Networks, a transformer-style architecture. It learns long-term spatial dependencies in the frequency domain with log-linear complexity, offering an efficient alternative to self-attention layers.
Trending
About
GFNet is an innovative AI tool that introduces Global Filter Networks for image classification, detailed in NeurIPS 2021 and T-PAMI. This transformer-style architecture efficiently learns long-term spatial dependencies by operating in the frequency domain, leveraging a 2D discrete Fourier transform, element-wise multiplication with learnable global filters, and a 2D inverse Fourier transform. It replaces traditional self-attention layers, offering a conceptually simple yet computationally efficient solution, especially for high-resolution feature maps. The PyTorch implementation is open-source, built upon pytorch-image-models and DeiT, and includes pre-trained models on ImageNet, along with scripts for evaluation, training, and transfer learning.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
