Picture for Meng-Hao Guo

Meng-Hao Guo

SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

Sep 18, 2022
Meng-Hao Guo, Cheng-Ze Lu, Qibin Hou, Zhengning Liu, Ming-Ming Cheng, Shi-Min Hu

Figure 1 for SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

Figure 2 for SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

Figure 3 for SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

Figure 4 for SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

* SegNeXt, a simple CNN for semantic segmentation. Code is available

Access Paper or Ask Questions

Visual Attention Network

Mar 08, 2022
Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu

Figure 1 for Visual Attention Network

Figure 2 for Visual Attention Network

Figure 3 for Visual Attention Network

Figure 4 for Visual Attention Network

* Code is available at https://github.com/Visual-Attention-Network

Access Paper or Ask Questions

Attention Mechanisms in Computer Vision: A Survey

Nov 15, 2021
Meng-Hao Guo, Tian-Xing Xu, Jiang-Jiang Liu, Zheng-Ning Liu, Peng-Tao Jiang, Tai-Jiang Mu, Song-Hai Zhang, Ralph R. Martin, Ming-Ming Cheng, Shi-Min Hu

Figure 1 for Attention Mechanisms in Computer Vision: A Survey

Figure 2 for Attention Mechanisms in Computer Vision: A Survey

Figure 3 for Attention Mechanisms in Computer Vision: A Survey

Figure 4 for Attention Mechanisms in Computer Vision: A Survey

* 27 pages, 9 figures

Access Paper or Ask Questions

Is Attention Better Than Matrix Decomposition?

Sep 09, 2021
Zhengyang Geng, Meng-Hao Guo, Hongxu Chen, Xia Li, Ke Wei, Zhouchen Lin

Figure 1 for Is Attention Better Than Matrix Decomposition?

Figure 2 for Is Attention Better Than Matrix Decomposition?

Figure 3 for Is Attention Better Than Matrix Decomposition?

Figure 4 for Is Attention Better Than Matrix Decomposition?

* ICLR 2021

Access Paper or Ask Questions

Subdivision-Based Mesh Convolution Networks

Jun 04, 2021
Shi-Min Hu, Zheng-Ning Liu, Meng-Hao Guo, Jun-Xiong Cai, Jiahui Huang, Tai-Jiang Mu, Ralph R. Martin

Figure 1 for Subdivision-Based Mesh Convolution Networks

Figure 2 for Subdivision-Based Mesh Convolution Networks

Figure 3 for Subdivision-Based Mesh Convolution Networks

Figure 4 for Subdivision-Based Mesh Convolution Networks

* Codes are available in https://github.com/lzhengning/SubdivNet

Access Paper or Ask Questions

Can Attention Enable MLPs To Catch Up With CNNs?

May 31, 2021
Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu, Dun Liang, Ralph R. Martin, Shi-Min Hu

Figure 1 for Can Attention Enable MLPs To Catch Up With CNNs?

* Computational Visual Media, 2021, accepted. 4 pages, 1 figure

Access Paper or Ask Questions

Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

May 31, 2021
Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu, Shi-Min Hu

Figure 1 for Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

Figure 2 for Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

Figure 3 for Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

Figure 4 for Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

* 11 pages, 6 figures. external attention and EAMLP

Access Paper or Ask Questions