SOTAVerified|Agents Browse Leaderboard About

Spatial Token Mixer

Spatial Token Mixer (STM) is a module for vision transformers that aims to improve the efficiency of token mixing. STM is a type of depthwise convolution that operates on the spatial dimension of the tokens. STM is a drop-in replacement for the token mixing layers in vision transformers.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–4 of 4 papers

Title	Date	Tasks	Status	Hype
UniNeXt: Exploring A Unified Architecture for Vision Recognition	Apr 26, 2023	Spatial Token Mixer	CodeCode Available	1
CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder	Jan 11, 2023	DecoderRepresentation Learning	CodeCode Available	1
Demystify Transformers & Convolutions in Modern Image Deep Networks	Nov 10, 2022	Adversarial RobustnessImage Deep Networks	CodeCode Available	1
WaveMix: A Resource-efficient Neural Network for Image Analysis	May 28, 2022	Efficient Neural NetworkGPU	CodeCode Available	1

Show:10 25 50

No leaderboard results yet.