Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 2,484

The DOI matches its Crossref record; 64 of the 64 references it cites were found in a registry or an index.

Swin Transformer V2: Scaling Up Capacity and Resolution

Open access
Liu, Ze, Hu, Han, Lin, Yutong, Yao, Zhuliang, Xie, Zhenda, Wei, Yixuan, Ning, Jia, Cao, Yue, Zhang, Zheng, Dong, Li, Wei, Furu, Guo, Baining·2022·2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

We present techniques for scaling Swin Transformer [35] up to 3 billion parameters and making it capable of training with images of up to 1,536x1,536 resolution. By scaling up capacity and resolution, Swin Transformer sets new records on four representative vision benchmarks: 84.0% top-1 accuracy on ImageNet- V2 image classification, 63.1 / 54.4 box / mask mAP on COCO object detection, 59.9 mIoU on ADE20K semantic segmentation, and 86.8% top-1 accuracy on Kinetics-400 video action classification. We tackle issues of training instability, and study how to effectively transfer models pre-trained at low resolutions to higher resolution ones. To this aim, several novel technologies are proposed: 1) a residual post normalization technique and a scaled cosine attention approach to improve the stability of large vision models; 2) a log-spaced continuous position bias technique to effectively transfer models pre-trained at low-resolution images and windows to their higher-resolution counterparts. In addition, we share our crucial implementation details that lead to significant savings of GPU memory consumption and thus make it feasi-ble to train large vision models with regular GPUs. Using these techniques and self-supervised pre-training, we suc-cessfully train a strong 3 billion Swin Transformer model and effectively transfer it to various vision tasks involving high-resolution images or windows, achieving the state-of-the-art accuracy on a variety of benchmarks. Code is avail-able at https://github.com/microsoft/Swin-Transformer.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52688.2022.01170

Cites

64 of 64 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 64 references

Research works printed but not linked: 14

  1. 2021, Microsoft, Using deepspeed and megatron to train megatron-turing nlg 530b the world's largest and most powerful generative language model
  2. liang, 2021, Cb-netv2 A composite backbone network architecture for obj ect detection
  3. li, 2021, Localvit Bringing locality to vision trans-formers
  4. 2020, Microsoft, Turing-NLG A 17-Billion-Parameter Language Model by Microsoft
  5. xiong, 2020, On layer normalization in the transformer architecture
  6. lei ba, 2016, Layer normalization
  7. touvron, 2020, Training data-efficient image transformers & distillation through attention, ArXiv Preprint
  8. wu, 0, Group normalization, Proceedings of the European Conference on Computer Vision (ECCV), 3
  9. vaswani, 2017, Attention is all you need, Advances in neural information processing systems, 5998
  10. radford, 2019, Language Models are Unsupervised Multitask Learners
  11. brock, 2021, Characterizing signal propagation to close the performance gap in unnormalized resnets, ArXiv Preprint
  12. cheng, 2021, Per-pixel classification is not all you need for semantic segmentation, ar Xiv
  13. ryoo, 2021, Tokenlearner What can 8 learned tokens do for images and videos?
  14. riquelme, 2021, Scaling Vision with Sparse Mixture of Experts

Cited by

See all 2,484

Metadata

Authors
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., Wei, F., & Guo, B.
Venue
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2022-06
Pages
11999-12009
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4312349930
Cited by
2,484
References
64
FWCI
197.21
Type
conference paper
Language
en
Open access
green
Funders
Microsoft

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Swin Transformer V2: Scaling Up Capacity and Resolution. https://app.cochat.ai/papers/10.1109/cvpr52688.2022.01170
The paper
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., Wei, F., & Guo, B. (2022). Swin Transformer V2: Scaling Up Capacity and Resolution. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr52688.2022.01170

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.