# RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality

Source: [RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality](<https://www.sota2.com/research/paper/68fa6c181e209131cea321cc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:33:54.408Z

Authors: Xiaohan Ding, Honghao Chen, Xiangyu Zhang, Jungong Han, Guiguang Ding

Published: 2021-12-21T10:28:17.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Segmentation on Cityscapes (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-val.md>): Semantic segmentation; Cityscapes (val); mIoU: 77.12.

- [Image Classification on ImageNet 1K (val) (Standard Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-standard-accuracy.md>): Image Classification; ImageNet-1k (val); Top-1 Accuracy: 81.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2112.11081>)

[PDF](<https://arxiv.org/pdf/2112.11081.pdf>)

[Implementation](<https://github.com/DingXiaoH/RepMLP>)