RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality

12/21/2021
by   Xiaohan Ding, et al.
1

Compared to convolutional layers, fully-connected (FC) layers are better at modeling the long-range dependencies but worse at capturing the local patterns, hence usually less favored for image recognition. In this paper, we propose a methodology, Locality Injection, to incorporate local priors into an FC layer via merging the trained parameters of a parallel conv kernel into the FC kernel. Locality Injection can be viewed as a novel Structural Re-parameterization method since it equivalently converts the structures via transforming the parameters. Based on that, we propose a multi-layer-perceptron (MLP) block named RepMLP Block, which uses three FC layers to extract features, and a novel architecture named RepMLPNet. The hierarchical design distinguishes RepMLPNet from the other concurrently proposed vision MLPs. As it produces feature maps of different levels, it qualifies as a backbone model for downstream tasks like semantic segmentation. Our results reveal that 1) Locality Injection is a general methodology for MLP models; 2) RepMLPNet has favorable accuracy-efficiency trade-off compared to the other MLPs; 3) RepMLPNet is the first MLP that seamlessly transfer to Cityscapes semantic segmentation. The code and models are available at https://github.com/DingXiaoH/RepMLP.

READ FULL TEXT

page 11

page 13

research
05/05/2021

RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition

We propose RepMLP, a multi-layer-perceptron-style neural network buildin...
research
09/20/2022

Dynamic Graph Message Passing Networks for Visual Recognition

Modelling long-range dependencies is critical for scene understanding ta...
research
11/18/2019

A Code injection Method for Rapid Docker Image Building

Docker images are built by layers, yet the current implementation has ma...
research
08/24/2022

gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window

Following the success in language domain, the self-attention mechanism (...
research
04/08/2023

MC-MLP:Multiple Coordinate Frames in all-MLP Architecture for Vision

In deep learning, Multi-Layer Perceptrons (MLPs) have once again garnere...
research
12/29/2022

BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons

This paper studies the problem of designing compact binary architectures...
research
09/14/2016

Very Simple Classifier: a Concept Binary Classifier toInvestigate Features Based on Subsampling and Localility

We propose Very Simple Classifier (VSC) a novel method designed to incor...

Please sign up or login with your details

Forgot password? Click here to reset