Global Filter Networks for Image Classification

by   Yongming Rao, et al.

Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases. These models are generally based on learning interaction among spatial locations from raw data. The complexity of self-attention and MLP grows quadratically as the image size increases, which makes these models hard to scale up when high-resolution features are required. In this paper, we present the Global Filter Network (GFNet), a conceptually simple yet computationally efficient architecture, that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our architecture replaces the self-attention layer in vision transformers with three key operations: a 2D discrete Fourier transform, an element-wise multiplication between frequency-domain features and learnable global filters, and a 2D inverse Fourier transform. We exhibit favorable accuracy/complexity trade-offs of our models on both ImageNet and downstream tasks. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness. Code is available at


page 10

page 15


Local-to-Global Self-Attention in Vision Transformers

Transformers have demonstrated great potential in computer vision tasks....

FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization

MLP-like models built entirely upon multi-layer perceptrons have recentl...

Separable Self-attention for Mobile Vision Transformers

Mobile vision transformers (MobileViT) can achieve state-of-the-art perf...

UHD Image Deblurring via Multi-scale Cubic-Mixer

Currently, transformer-based algorithms are making a splash in the domai...

Fourier Disentangled Space-Time Attention for Aerial Video Recognition

We present an algorithm, Fourier Activity Recognition (FAR), for UAV vid...

FFCNet: Fourier Transform-Based Frequency Learning and Complex Convolutional Network for Colon Disease Classification

Reliable automatic classification of colonoscopy images is of great sign...

Multi Resolution Analysis (MRA) for Approximate Self-Attention

Transformers have emerged as a preferred model for many tasks in natural...

Code Repositories


Global Filter Networks for Image Classification

view repo