Journal Home > Volume 8 , Issue 3
Computational Visual Media 2022, 8(3): 415-424 https://doi.org/10.1007/s41095-022-0274-8
Research Article | Open Access | Issue | Published: 16 March 2022

PVT v2: Improved baselines with Pyramid Vision Transformer

Show Author's Information Wenhai Wang1,2( ),  Enze Xie3,  Xiang Li4,  Deng-Ping Fan5,  Kaitao Song4,  Ding Liang6,  Tong Lu2,  Ping Luo3,  Ling Shao7
Shanghai AI Laboratory, Shanghai 200232, China
Department of Computer Science and Technology, NanjingUniversity, Nanjing 210023, China
Department of Computer Science, the University ofHong Kong, Hong Kong 999077, China
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210014, China
Computer Vision Lab, ETH Zurich, Zurich 8092, Switzerland
SenseTime, Beijing 100080, China
Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates
Keywords:
image classification, object detection, semantic segmentation, transformers, dense prediction
Cite this article:
Wang W, Xie E, Li X, et al. PVT v2: Improved baselines with Pyramid Vision Transformer. Computational Visual Media, 2022, 8(3): 415-424. https://doi.org/10.1007/s41095-022-0274-8
Download citation
EndNote(RIS)
BibTeX

1775

Views

106

Downloads

Citations

569

Crossref

432

WoS

571

Scopus

11

CSCD

Abstract Full text About this article

Transformers have recently lead to encouraging progress in computer vision. In this work, we present new baselines by improving the original Pyramid Vision Transformer (PVT v1) by adding three designs: (i) a linear complexity attention layer, (ii) an overlapping patch embedding, and (iii) a convolutional feed-forward network. With these modifications, PVT v2 reduces the computational complexity of PVT v1 to linearity and provides significant improvements on fundamental vision tasks such as classification, detection, and segmentation. In particular, PVT v2 achieves comparable or better performance than recent work such as the Swin transformer. We hope this work will facilitate state-of-the-art transformer research in computer vision. Code is available at https://github.com/whai362/PVT.


menu
Abstract
Full text
Outline
About this article

PVT v2: Improved baselines with Pyramid Vision Transformer

Show Author's information Wenhai Wang1,2( ), Enze Xie3, Xiang Li4, Deng-Ping Fan5, Kaitao Song4, Ding Liang6, Tong Lu2, Ping Luo3, Ling Shao7
Shanghai AI Laboratory, Shanghai 200232, China
Department of Computer Science and Technology, NanjingUniversity, Nanjing 210023, China
Department of Computer Science, the University ofHong Kong, Hong Kong 999077, China
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210014, China
Computer Vision Lab, ETH Zurich, Zurich 8092, Switzerland
SenseTime, Beijing 100080, China
Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates

Abstract

Transformers have recently lead to encouraging progress in computer vision. In this work, we present new baselines by improving the original Pyramid Vision Transformer (PVT v1) by adding three designs: (i) a linear complexity attention layer, (ii) an overlapping patch embedding, and (iii) a convolutional feed-forward network. With these modifications, PVT v2 reduces the computational complexity of PVT v1 to linearity and provides significant improvements on fundamental vision tasks such as classification, detection, and segmentation. In particular, PVT v2 achieves comparable or better performance than recent work such as the Swin transformer. We hope this work will facilitate state-of-the-art transformer research in computer vision. Code is available at https://github.com/whai362/PVT.

Keywords: image classification, object detection, semantic segmentation, transformers, dense prediction

References(42)

[1]
Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; Weissenborn, D.; Zhai, X.; Unterthiner, T.; Dehghani, M.; Minderer, M.; Heigold, G.; S. Gelly, S.; et al. An image is worth 16×16 words: Transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations, 2021.
[2]
Touvron, H.; Cord, M.; Douze, M.; Massa, F.; Jégou, H. Training data-efficient image transformers & distillation through attention. In: Proceedings of the 38th International Conference on Machine Learning, 2021.
[3]
Wang, W.; Xie, E.; Li, X.; Fan, D.-P.; Song, K.; Liang, D.; Lu, T.; Luo, P.; Shao, L. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 568-578, 2021.
DOI
[4]
Wu, H.; Xiao, B.; Codella, N.; Liu, M.; Dai, X.; Yuan, L.; Zhang, L. CvT: Introducing convolutions to vision transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 22-31, 2021.
DOI
[5]
Liu, Z.; Lin, Y.; Cao, Y.; Hu, H.; Wei, Y.; Zhang, Z.; Lin, S.; Guo, B. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 10012-10022, 2021.
DOI
[6]
Xu, W.; Xu, Y.; Chang, T.; Tu, Z. Co-scale conv-attentional image transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 9981-9990, 2021.
DOI
[7]
Graham, B.; El-Nouby, A.; Touvron, H.; Stock, P.; Joulin, A.; Jégou, H. LeViT: A vision transformer in ConvNet’s clothing for faster inference. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 12259-12269, 2021.
DOI
[8]
Chu, X.; Tian, Z.; Wang, Y.; Zhang, B.; Ren, H.; Wei, X.; Xia, H.; Shen, C. Twins: Revisiting the design of spatial attention in vision transformers. In: Proceedings of the 35th Conference on Neural Information Processing Systems, 2021.
[9]
Lin, T. Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollár, P.; Zitnick, C. L. Microsoft COCO: Common objects in context. In: Computer Vision - ECCV 2014. Lecture Notes in Computer Science, Vol. 8693. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer Cham, 740-755, 2014.
DOI
[10]
Zhou, B. L.; Zhao, H.; Puig, X.; Fidler, S.; Barriuso, A.; Torralba, A. Scene parsing through ADE20K dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5122-5130, 2017.
DOI
[11]
Dong, B.; Wang, W.; Fan, D.-P.; Li, J.; Fu, H.; Shao, L. Polyp-PVT: Polyp segmentation with pyramid vision transformers. arXiv preprint arXiv:2108.06932, 2021.
Google Scholar
[12]
Li, X.; Wang, W.; Wu, L.; Chen, S.; Hu, X.; Li, J.; Tang, J.; Yang, J. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. In: Proceedings of the 34th Conference on Neural Information Processing Systems, 2020.
DOI
[13]
He, K. M.; Zhang, X. Y.; Ren, S. Q.; Sun, J. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, 1026-1034, 2015.
[14]
Deng, J.; Dong, W.; Socher, R.; Li, L. J.; Kai, L.; Li, F. F. ImageNet: A large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 248-255, 2009.
DOI
[15]
Yuan, L.; Chen, Y.; Wang, T.; Yu, W.; Shi, Y.; Jiang, Z.; Tay, F. E.; Feng, J.; Yan, S. Tokens-to-token ViT: Training vision transformers from scratch on ImageNet. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 558-567, 2021.
DOI
[16]
Han, K.; Xiao, A.; Wu, E.; Guo, J.; Xu, C.; Wang, Y. Transformer in transformer. arXiv preprint arXiv:2103.00112, 2021.
Google Scholar
[17]
Chu, X.; Tian, Z.; Zhang, B.; Wang, X.; Wei, X.; Xia, H.; Shen, C. Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882, 2021.
Google Scholar
[18]
Chen, C.-F.; Fan, Q.; Panda, R. CrossViT: Cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 357-366, 2021.
DOI
[19]
Li, Y.; Zhang, K.; Cao, J.; Timofte, R.; van Gool, L. LocalViT: Bringing locality to vision transformers. arXiv preprint arXiv:2104.05707, 2021.
Google Scholar
[20]
Islam, M. A.; Jia, S.; Bruce, N. D. B. How much position information do convolutional neural networks encode? In: Proceedings of the International Conference on Learning Representations, 2020.
[21]
Howard, A. G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T; Andreetto, M.; Adam, H. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
Google Scholar
[22]
Hendrycks, D.; Gimpel, K. Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415, 2016.
Google Scholar
[23]
Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, L.; Polosukhin, I. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 6000-6010, 2017.
[24]
He, K. M.; Zhang, X. Y.; Ren, S. Q.; Sun, J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778, 2016.
[25]
Xie, S. N.; Girshick, R.; Dollar, P.; Tu, Z. W.; He, K. M. Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5987-5995, 2017.
DOI
[26]
Radosavovic, I.; Kosaraju, R. P.; Girshick, R.; He, K. M.; Dollár, P. Designing network design spaces. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10425-10433, 2020.
DOI
[27]
Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S. A.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; et al. ImageNet large scale visual recognition challenge. International Journal of Computer Vision Vol. 115, No. 3, 211-252, 2015.
DOI Google Scholar
[28]
Szegedy, C.; Liu, W.; Jia, Y. Q.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1-9, 2015.
DOI
[29]
Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818-2826, 2016.
DOI
[30]
Zhang, H.; Cisse, M.; Dauphin, Y. N.; Lopez-Paz, D. mixup: Beyond empirical risk minimization. In: Proceedings of the International Conference on Learning Representations, 2018.
[31]
Zhong, Z.; Zheng, L.; Kang, G. L.; Li, S. Z.; Yang, Y. Random erasing data augmentation. Proceedings of the AAAI Conference on Artificial Intelligence Vol. 34, No. 7, 13001-13008, 2020.
DOI Google Scholar
[32]
Loshchilov, I.; Hutter, F. Decoupled weight decay regularization. In: Proceedings of the International Conference on Learning Representations, 2019.
[33]
Loshchilov, I.; Hutter, F. SGDR: Stochastic gradient descent with warm restarts. In: Proceedings of theInternational Conference on Learning Representations, 2017.
[34]
Lin, T. Y.; Goyal, P.; Girshick, R.; He, K. M.; Dollár, P. Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, 2999-3007, 2017.
DOI
[35]
He, K. M.; Gkioxari, G.; Dollár, P.; Girshick, R. Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, 2980-2988, 2017.
[36]
Cai, Z. W.; Vasconcelos, N. Cascade R-CNN: Delving into high quality object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6154-6162, 2018.
DOI
[37]
Zhang, S. F.; Chi, C.; Yao, Y. Q.; Lei, Z.; Li, S. Z. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9756-9765, 2020.
DOI
[38]
Sun, P. Z.; Zhang, R. F.; Jiang, Y.; Kong, T.; Xu, C. F.; Zhan, W.; Tomizuka, M.; Li, L.; Yuan, Z.; Wang, C.; et al. Sparse R-CNN: End-to-end object detection with learnable proposals. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 14449-14458, 2021.
DOI
[39]
Glorot, X.; Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, 249-256, 2010.
[40]
Chen, K.; Wang, J. Q.; Pang, J. M.; Cao, Y. H.; Xiong, Y.; Li, X.; Sun, S.; Feng, W.; Liu, Z.; Xu, J.; et al. MMDetection: Open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155, 2019.
Google Scholar
[41]
Kirillov, A.; Girshick, R.; He, K. M.; Dollár, P. Panoptic feature pyramid networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6392-6401, 2019.
DOI
[42]
Chen, L. C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A. L. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 40, No. 4, 834-848, 2018.
DOI Google Scholar
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 22 December 2021
Accepted: 08 February 2022
Published: 16 March 2022
Issue date: September 2022

Copyright

© The Author(s) 2022.

Acknowledgements

This work was supported by the NationalNatural Science Foundation of China under Grant Nos. 61672273 and 61832008, the Science Foundation for Distinguished Young Scholars of Jiangsu under Grant No. BK20160021, the Postdoctoral Innovative Talent Support Program of China under Grant Nos. BX20200168 and 2020M681608, and the General Research Fund of Hong Kong under Grant No. 27208720.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduc-tion in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Other papers from this open access journal are available free of charge from http://www.springer.com/journal/41095. To submit a manuscript, please go to https://www. editorialmanager.com/cvmj.

Return