Pyramid Swin Transformer: Different-Size Windows Swin Transformer for Image Classification and Object Detection

Chenyu Wang, Chenyu Wang, Toshio Endo, Takahiro Hirofuchi, Tsutomu Ikegami

2023

Abstract

We present the Pyramid Swin Transformer for object detection and image classification, by taking advantage of more shift window operations, smaller and more different size windows. We also add a Feature Pyramid Network for object detection, which produces excellent results. This architecture is implemented in four stages, containing different size window layers. We test our architecture on ImageNet classification and COCO detection. Pyramid Swin Transformer achieves 85.4% accuracy on ImageNet classification and 54.3 box AP on COCO.

Paper Citation

in Harvard Style

Wang C., Endo T., Hirofuchi T. and Ikegami T. (2023). Pyramid Swin Transformer: Different-Size Windows Swin Transformer for Image Classification and Object Detection. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 583-590. DOI: 10.5220/0011675800003417

in Bibtex Style

@conference{visapp23,
author={Chenyu Wang and Toshio Endo and Takahiro Hirofuchi and Tsutomu Ikegami},
title={Pyramid Swin Transformer: Different-Size Windows Swin Transformer for Image Classification and Object Detection},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={583-590},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011675800003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Pyramid Swin Transformer: Different-Size Windows Swin Transformer for Image Classification and Object Detection
SN - 978-989-758-634-7
AU - Wang C.
AU - Endo T.
AU - Hirofuchi T.
AU - Ikegami T.
PY - 2023
SP - 583
EP - 590
DO - 10.5220/0011675800003417
PB - SciTePress