Hire-MLP: Vision MLP via Hierarchical Rearrangement
- URL: http://arxiv.org/abs/2108.13341v1
- Date: Mon, 30 Aug 2021 16:11:04 GMT
- Title: Hire-MLP: Vision MLP via Hierarchical Rearrangement
- Authors: Jianyuan Guo, Yehui Tang, Kai Han, Xinghao Chen, Han Wu, Chao Xu,
Chang Xu and Yunhe Wang
- Abstract summary: Hire-MLP is a simple yet competitive vision architecture via rearrangement.
The proposed Hire-MLP architecture is built with simple channel-mixing operations, thus enjoys high flexibility and inference speed.
Experiments show that our Hire-MLP achieves state-of-the-art performance on the ImageNet-1K benchmark.
- Score: 58.33383667626998
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper presents Hire-MLP, a simple yet competitive vision MLP
architecture via hierarchical rearrangement. Previous vision MLPs like
MLP-Mixer are not flexible for various image sizes and are inefficient to
capture spatial information by flattening the tokens. Hire-MLP innovates the
existing MLP-based models by proposing the idea of hierarchical rearrangement
to aggregate the local and global spatial information while being versatile for
downstream tasks. Specifically, the inner-region rearrangement is designed to
capture local information inside a spatial region. Moreover, to enable
information communication between different regions and capture global context,
the cross-region rearrangement is proposed to circularly shift all tokens along
spatial directions. The proposed Hire-MLP architecture is built with simple
channel-mixing MLPs and rearrangement operations, thus enjoys high flexibility
and inference speed. Experiments show that our Hire-MLP achieves
state-of-the-art performance on the ImageNet-1K benchmark. In particular,
Hire-MLP achieves an 83.4\% top-1 accuracy on ImageNet, which surpasses
previous Transformer-based and MLP-based models with better trade-off for
accuracy and throughput.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.