TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

Wenqiang Zhang, Zilong Huang, Guozhong Luo, Tao Chen, Xinggang Wang, Wenyu Liu, Gang Yu, Chunhua Shen; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 12083-12093

Abstract


Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present a mobile-friendly architecture named Token Pyramid Vision Transformer (TopFormer). The proposed TopFormer takes Tokens from various scales as input to produce scale-aware semantic features, which are then injected into the corresponding tokens to augment the representation. Experimental results demonstrate that our method significantly outperforms CNN- and ViT-based networks across several semantic segmentation datasets and achieves a good trade-off between accuracy and latency. On the ADE20K dataset, TopFormer achieves 5% higher accuracy in mIoU than MobileNetV3 with lower latency on an ARM-based mobile device. Furthermore, the tiny version of TopFormer achieves real-time inference on an ARM-based mobile device with competitive results. The code and models are available at https://github.com/hustvl/TopFormer.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Wenqiang and Huang, Zilong and Luo, Guozhong and Chen, Tao and Wang, Xinggang and Liu, Wenyu and Yu, Gang and Shen, Chunhua}, title = {TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {12083-12093} }