RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality

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

Allbwn ymchwil: Cyfraniad arall

13 Dyfyniadau(SciVal)


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

Iaith wreiddiolSaesneg
CyhoeddwrIEEE Press
Nifer y tudalennau10
ISBN (Argraffiad)1063-6919, 978-1-6654-6946-3
ISBN (Electronig)9781665469463
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 2022

Cyfres gyhoeddiadau

EnwProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Argraffiad)1063-6919

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn