Skip to content

[WACV'25] Official implementation of "PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplane MRI Slices".

License

Notifications You must be signed in to change notification settings

mkang315/PK-YOLO

Repository files navigation

Official PK-YOLO

Build Build

Description

This is the source code for the paper titled "PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplane MRI Slices" accepted by the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025), of which I am the first author. The paper is available to download from the WACV 2025 open access provided by the Computer Vision Foundation, IEEE Xplore Proceedings, or arXiv(the latest version).

Model

Installation

Install requirements.txt in a Python>=3.8.0 environment, including PyTorch>=1.7.0.

pip install -r requirements.txt
Training
python train_dual.py

Referencing Guide

Please cite the paper if using this repository. Here is a guide to referencing this work in various styles for formatting your references:

Plain Text

  • IEEE Full Name Reference Style
    Ming Kang, Fung Fung Ting, Raphaël C.-W. Phan, and Chee-Ming Ting. Pk-yolo: Pretrained knowledge guided yolo for brain tumor detection in multiplane mri slices. In WACV, pages 3732–3741, 2025.
    NOTE: This is a modification to the standard IEEE Reference Style and used by most IEEE/CVF conferences, including CVPR, ICCV, and WACV, to render first names in the bibliography as "Firstname Lastname" rather than "F. Lastname" or "Lastname, F.".
     - IJCAI Full Name-Year Variation
    [Kang et al., 2025] Ming Kang, Fung Fung Ting, Raphaël C.-W. Phan, and Chee-Ming Ting. Pk-yolo: Pretrained knowledge guided yolo for brain tumor detection in multiplane mri slices. In Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3732–3741, Piscataway, NJ, February 2025. IEEE.
     - ACL Full Name-Year Variation
    Ming Kang, Fung Fung Ting, Raphaël C.-W. Phan, and Chee-Ming Ting. 2025. Pk-yolo: Pretrained knowledge guided yolo for brain tumor detection in multiplane mri slices. In Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3732–3741, Piscataway, NJ. IEEE.

  • IEEE Reference Style
    M. Kang, F. F. Ting, R. C.-W. Phan, and C.-M. Ting, "Pk-yolo: Pretrained knowledge guided yolo for brain tumor detection in multiplane mri slices," in Proc. Winter Conf. Appl. Comput. Vis. (WACV), Tucson, AZ, USA, Feb. 28–Mar. 4, 2025, pp. 3732–3741.
    NOTE: City of Conf., Abbrev. State, Country, Month & Day(s) are optional.

  • Nature Reference Style
    Kang, M., Ting, C.-M., Ting, F. F. & Phan, R. C.-W. PK-YOLO: pretrained knowledge guided YOLO for brain tumor detection in multiplane MRI slices. In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 3732–3741 (IEEE, 2025).

  • Springer Reference Style
    Kang, M., Ting, F.F., Phan, R.C.-W., Ting, C.-M.: PK-YOLO: pretrained knowledge guided YOLO for brain tumor detection in multiplane MRI slices. In: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3732–3741. IEEE, Piscataway (2025)
    NOTE: ECCV and MICCAI conference proceedings are part of the book series LNCS in which Springer's format for bibliographical references is strictly enforced. LNCS stands for Lecture Notes in Computer Science.

  • Elsevier Numbered Style
    M. Kang, F.F. Ting, R.C.-W. Phan, C.-M. Ting, PK-YOLO: pretrained knowledge guided YOLO for brain tumor detection in multiplane MRI slices, in: Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 3732–3741.
    NOTE: Day(s) Month Year, City, Abbrev. State, Country of Conference, Publiser, and Place of Publication are optional and omitted.

  • Elsevier Name–Date (Harvard) Style
    Kang, M., Ting, F.F., Phan, R.C.-W., Ting, C.-M., 2025. PK-YOLO: pretrained knowledge guided YOLO for brain tumor detection in multiplane MRI slice. In: Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 28 Februray–4 March 2025, Tucson, AZ, USA. IEEE, Piscataway, New York, USA, pp. 3732–3741.
    NOTE: Day(s) Month Year, City, Abbrev. State, Country of Conference, Publiser, and Place of Publication are optional.

  • Elsevier Vancouver Style
    Kang M, Ting FF, Phan RC-W, Ting C-M. PK-YOLO: pretrained knowledge guided YOLO for brain tumor detection in multiplane MRI slice. In: Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV); 2025 Feb 28–Mar 4; Tucson, AZ, USA. Piscataway: IEEE; 2025. p. 3732–41.

  • Elsevier Embellished Vancouver Style
    Kang M, Ting FF, Phan RC-W, Ting C-M. PK-YOLO: pretrained knowledge guided YOLO for brain tumor detection in multiplane MRI slice. In: Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV); 2025 Feb 28–Mar 4; Tucson, AZ, USA. Piscataway: IEEE; 2025. p. 3732–41.

  • APA7 (Author–Date) Style
    Kang, M., Ting, F. F., Phan, R. C.-W., & Ting, C.-M. (2025). PK-YOLO: Pretrained knowledge guided YOLO for brain tumor detection in multiplane MRI slice. In Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 3732–3741). IEEE. https://doi.org/10.1109/WACV61041.2025.00367
     - ICML (Author–Year) Variation
    Kang, M., Ting, F. F., Phan, R. C.-W., and Ting, C.-M. PK-YOLO: Pretrained knowledge guided YOLO for brain tumor detection in multiplane MRI slice. In Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3732–3741, Piscataway, NJ, 2025. IEEE.
    NOTE: For NeurIPS and ICLR, any reference/citation style is acceptable as long as it is used consistently. The sample of references in Formatting Instructions For NeurIPS almost follows APA7 (author–date) style and that in Formatting Instructions For ICLR Conference Submissions is similar to IJCAI full name-year variation.

BibTeX Format

\begin{thebibliography}{1}
\bibitem{Kang25Pkyolo} M. Kang, F. F. Ting, R. C.-W. Phan, and C.-M. Ting, "Pk-yolo: Pretrained knowledge guided yolo for brain tumor detection in multiplane mri slices," in {\emph Proc. Winter Conf. Appl. Comput. Vis. (WACV)}, Tucson, AZ, USA, Feb. 28--Mar. 4, 2025, pp. 3732--3741.
\end{thebibliography}
@inproceedings{Kang25Pkyolo,
  author = "Ming Kang and Fung Fung Ting and Rapha{\"e}l C.-W. Phan and Chee-Ming Ting",
  title = "Pk-yolo: Pretrained knowledge guided yolo for brain tumor detection in multiplane mri slices",
  booktitle = "Proc. Winter Conf. Appl. Comput. Vis. (WACV)",
  % booktitle = WACV, %% IEEE Full Name Reference Style
  address = "Tucson, AZ, USA, Feb. 28--Mar. 4",
  pages = "3732--3741",
  year = "2025"
}
@inproceedings{Kang25Pkyolo,
  author = "Kang, Ming and Ting, Fung Fung and Phan, Rapha{\"e}l C.-W. and Ting, Chee-Ming",
  title = "{PK-YOLO}: pretrained knowledge guided {YOLO} for brain tumor detection in multiplane {MRI} slices",
  editor = "",
  booktitle = "2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)",
  series = "",
  volume = "",
  pages = "3732--3741",
  publisher = "IEEE",
  address = "Piscataway",
  year = "2025",
  doi= "10.1109/WACV61041.2025.00367",
  url = "https://doi.org/10.1109/WACV61041.2025.00367"
}

NOTE: Please remove some optional BibTeX fields/tags such as series, volume, address, url, and so on if the LaTeX compiler produces an error. Author names may be manually modified if not automatically abbreviated by the compiler under the control of the bibliography/reference style (i.e., .bst) file. The BibTex citation key may be bib1, b1, or ref1 when references appear in numbered style in which they are cited. The quotation mark pair "" in the field could be replaced by the brace {}, whereas the brace {} in the BibTeX field/tag title plays a role of keeping letters/characters/text original lower/uppercases or sentence/capitalized cases unchanged while using Springer Nature bibliography style files, for example, sn-nature.bst.

License

PK-YOLO is released under the GNU General Public License v3.0. Please see the LICENSE file for more information.

Copyright Notice

Many utility codes of our project base on the codes of RepViT, SparK, YOLOv9, and Focaler-IoU repositories.