弱いラベル・少数ラベルから学ぶ

Selected Pattern Recognition, 112425, 2025.

Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning

Kaito Shiku, Shinnosuke, Matsuo, Daiki Suehiro, and Ryoma Bise

集合の多数派クラスのみを使い、個々のインスタンスのクラスを推定します。

論文を見る ↗

Selected MICCAI 2024 · 部分割合ラベル

Learning from Partial Label Proportions for Whole Slide Image Segmentation

1. Leveraging Label Proportion Prior for Class-Imbalanced Semi-Supervised Learning
   Kohki Akiba, Shinnosuke Matsuo, Shota Harada, and Ryoma Bise · IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026.
2. Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
   Kaito Shiku, Shinnosuke, Matsuo, Daiki Suehiro, and Ryoma Bise · Pattern Recognition, 112425, 2025.
3. Theoretical Proportion Label Perturbation for Learning from Label Proportions in Large Bags
   Shunsuke Kubo, Shinnosuke Matsuo, Daiki Suehiro, Kazuhiro Terada, Hiroaki Ito, Akihiko Yoshizawa and Ryoma Bise · European Conference on Artificial Intelligence (ECAI), 2024. (acceptted, acceptance rate:23% (547/2344) )
4. Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning
   Takehiro Yamane, Itaru Tsuge, Susumu Saito, and Ryoma Bise · MICCAI Workshop (ADSMI), 2024. (acceptted)
5. Learning from Partial Label Proportions for Whole Slide Image Segmentation
   Shinnosuke Matsuo, Daiki Suehiro, Seiichi Uchida, Hiroaki Ito, Kazuhiro Terada, Akihiko Yoshizawa and Ryoma Bise · International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI),2024. (Early Accept, acceptance rate:11%)
6. Diameter-based pseudo labeling for pathological image segmentation
   Yuki Shigeyasu, Shota Harada, Akihiko Yoshizawa, Kazuhiro Terada, and Ryoma Bisee · International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC),2024
7. A data augmentation approach that ensures the reliability of foregrounds in medical image segmentation
   Xiaoqing Liu, KenjiOno, and Ryoma Bise · Image and Vision Computing, 147, 105056, 2024. (IF:4.2)
8. Counting Network for Learning from Majority Label
   Kaito Shiku, Shinnosuke Matsuo, Daiki Suehiro, and Ryoma Bise · IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP),2024,(Top Conference in Signal Processing)
9. MixBag: Bag-Level Data Augmentation for Learning from Label Proportions
   Takanori Asanomi, Shinnosuke Matsuo, Daiki Suehiro and Ryoma Bise · International Conference on Computer Vision (ICCV),2023,(top conference in computer vision)
10. Proportion Estimation by Masked Learning from Label Proportion
    Takumi Okuo, Kazuya Nishimura, Hiroaki Ito, Kazuhiro Terada, Akihiko Yoshizawa, and Ryoma Bise · Workshop on MICCAI: DALI, pp.117-126, 2023.
11. Learning From Label Proportion with Online Pseudo-Label Decision by Regret Minimization
    Shinnosuke Matsuo, Ryoma Bise, Seiichi Uchida, and Daiki Suehiro · IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2023),2023 (top conference in signal processing)
12. Spatial Distribution-based Pseudo Labeling for Pathological Image Segmentation
    Yuki Shigeyasu, Shota Harada, Kengo Araki, Akihiko Yoshizawa, Kazuhiro Terada, and Ryoma Bise · IEEE International Symposium on Biomedical Imaging (ISBI), 2023.
13. Mixing Data Augmentation with Preserving Foreground Regions in Medical Image Segmentation
    Xiaoqing Liu, Kenji Ono, and Ryoma Bise · IEEE International Symposium on Biomedical Imaging (ISBI), 2023. (Oral)
14. Soft and Self Constrained Clustering for Group-Based Labeling
    Shota Harada, Ryoma Bise, Hideaki Hayashi, Kiyohito Tanaka, and Seiichi Uchida · Medical Image Analysis, https://doi.org/10.1016/j.media.2021.102097, 2021, May (in press, top journal in medicalImage analysis, IF:11.148)
15. Negative Pseudo Labeling using Class Proportion for Semantic Segmentation in Pathology
    H. Tokunaga, B.K. Iwana, Y. Teramoto, A. Yoshizawa, and R. Bise · 16th European Conference on Computer Vision (ECCV2020) 2020, (accepted, Top Conference in Computer Vision, acceptance rate:27%)
16. Efficient Soft-Constrained Clustering for Group-Based Labeling
    R. Bise, K. Abe, H. Hayashi, K. Tanaka, and S. Uchida · International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI2019), 2019, (top conference in medial image analysis, acceptance rate:31%)
17. Scribbles for Metric Learning
    D. Harada, R. Bise, H. Tokunaga, W. Ohyama, S. Oka, T. Fujimori, and S. Uchida · Proceedings of 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2019.
18. Semi-Supervised Learning for Biomedical Image Segmentation via Forest Oriented Super Pixels(Voxels)
    L. Gu, Y. Zheng, R. Bise, I. Sato, N. Imanishi, and S. Aiso · International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp.702-710, 2017,(top conference in medial image analysis, acceptance rate:33%)

Publication一覧を見る →