CV

Education

• Ph.D in Version Control Theory, GitHub University, 2018 (expected)
• M.S. in Jekyll, GitHub University, 2014
• B.S. in GitHub, GitHub University, 2012

Work experience

• Spring 2024: Academic Pages Collaborator
  • GitHub University
  • Duties includes: Updates and improvements to template
  • Supervisor: The Users
• Fall 2015: Research Assistant
  • GitHub University
  • Duties included: Merging pull requests
  • Supervisor: Professor Hub
• Summer 2015: Research Assistant
  • GitHub University
  • Duties included: Tagging issues
  • Supervisor: Professor Git

Skills

• Skill 1
• Skill 2
  • Sub-skill 2.1
  • Sub-skill 2.2
  • Sub-skill 2.3
• Skill 3

Publications

Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes

Sota Kato, Hinako Mitsuoka, Kazuhiro Hotta. (2024). "Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes." ECCV 2024 Workshop (CADL). (Oral)

Generalized SAMを用いた可変な入力画素数に対するSAMの追加学習

加藤 聡太, 堀田 一弘. (2024). "Generalized SAMを用いた可変な入力画素数に対するSAMの追加学習." MIRU2024.

深層学習を用いた偏りのあるデータに対して頑健な学習手法に関する研究

加藤 聡太, 堀田 一弘. (2024). "深層学習を用いた偏りのあるデータに対して頑健な学習手法に関する研究." CVIM.

Automatic enhancement preprocessing for segmentation of low quality cell images

Sota Kato, Kazuhiro Hotta. (2024). "Automatic enhancement preprocessing for segmentation of low quality cell images." Scientific Reports, 14, 3619. (Impact factor: 4.997)

LITE-HRNET PLUS: FAST AND ACCURATE FACIAL LANDMARK DETECTION

Sota Kato, Kazuhiro Hotta, Yuhki Hatakeyama, Yoshinori Konishi. (2023). "LITE-HRNET PLUS: FAST AND ACCURATE FACIAL LANDMARK DETECTION." IEEE ICIP 2023. pp.1500-1504. (Poster)

Enlarged Large Margin Loss For Imbalanced Classification

Sota Kato, Kazuhiro Hotta. (2023). "Enlarged Large Margin Loss For Imbalanced Classification." IEEE SMC 2023. pp.1696-1701. (Oral)

クラス不均衡な画像分類に対するLarge Marginに基づいた新たな損失関数の提案

不正解クラスの交差エントロピー最大化を用いたLong-tailed Classification

One-shot and Partially-Supervised Cell Image Segmentation Using Small Visual Prompt

Sota Kato, Kazuhiro Hotta. (2023). "One-shot and Partially-Supervised Cell Image Segmentation Using Small Visual Prompt." CVPR 2023 Workshop (CVMI). pp.4294-4303. (Oral)

事前学習済みモデルを用いた細胞画像に対する One-shot/Semi-supervised Semantic Segmentation

Improvement of Vision Transformer Using Word Patches

Ayato Takama, Sota Kato, Satoshi Kamiya, Kazuhiro Hotta. (2023). "Improvement of Vision Transformer Using Word Patches." VISAPP 2023. pp.731-736. (Poster)

Semantic Segmentation by Semi-Supervised Learning Using Time Series Constraint

Takahiro Mano, Sota Kato, Kazuhiro Hotta. (2023). "Semantic Segmentation by Semi-Supervised Learning Using Time Series Constraint." VISAPP 2023. pp.708-714. (Poster)

Expanded Tube Attention for Tubular Structure Segmentation

Sota Kato, Kazuhiro Hotta. (2023). "Expanded Tube Attention for Tubular Structure Segmentation." International Journal of Computer Assisted Radiology and Surgery. (Impact factor: 3.0)

Adaptive t-vMF Dice Loss: An Effective Expansion of Dice Loss for Medical Image Segmentation

Sota Kato, Kazuhiro Hotta. (2023). "Adaptive t-vMF Dice Loss: An Effective Expansion of Dice Loss for Medical Image Segmentation." Computers in Biology and Medicine, 107695. (Impact factor: 7.7)

Earth Mover’s Distanceを用いた深層学習の学習過程の解析

Adaptive t-vMF Dice lossを用いたMulit-class Medical Image Segmentationの精度改善

Expanded tube attention module を用いたtubular structure segmentation

Lite-HRNet Plusを用いた高速・高精度な顔ランドマーク検出

Classification and visual explanation for COVID-19 pneumonia from CT images using triple learning

Kato, S., Oda, M., Mori, K., Shimizu, A., Otake, Y., Hashimoto, M., Akashi, T., Hotta, K. (2022). "Classification and visual explanation for COVID-19 pneumonia from CT images using triple learning." Scientific Reports, 12(1), 1-13. (Impact factor: 4.996)

Automatic Preprocessing and Ensemble Learning for Cell Segmentation with Low Quality

Sota Kato, Kazuhiro Hotta. (2021). "Automatic Preprocessing and Ensemble Learning for Cell Segmentation with Low Quality." IEEE SMC 2021. pp.1828-1833. (Oral)

クラス不均衡データセットに対するMSE Lossに基づいた学習法の提案

クラス確率行列の最適化による多クラスセマンティックセグメンテーションの精度向上

Contrastive Learningを用いた肺野CT画像から COVID-19の自動判定

距離学習を用いたCT画像からのCOVID-19の識別

加藤 聡太, 堀田 一弘. (2021). "距離学習を用いたCT画像からのCOVID-19の識別." MEDICAL IMAGING TECHNOLOGY, 39(1), 20-26.

Pitching Classification and Habit Detection by V-Net

Sota Kato, Kazuhiro Hotta. (2020). "Pitching Classification and Habit Detection by V-Net." VISAPP 2020. pp.615-621. (Poster)

Cell Segmentation by Image-to-Image Translation using Multiple Different Discriminators

Sota Kato, Kazuhiro Hotta. (2020). "Cell Segmentation by Image-to-Image Translation using Multiple Different Discriminators." BIOSIGNALS 2020. pp.330-335. (Oral)

Image Translation for Cell Image Segmentation Using Deep Learning

Sota Kato, Kazuhiro Hotta. (2019). "Image Translation for Cell Image Segmentation Using Deep Learning." International Conference on Systems Biology 2019. (Poster)

Automatic Image Preprocessing Method Using Deep Learning

Sota Kato, Kazuhiro Hotta. (2019). "Automatic Image Preprocessing Method Using Deep Learning." Resonance Bio International Symposium 2019. (Poster)

Cell Image Segmentation by Pix2pix Using Multiple Different Discriminators

Sota Kato, Kazuhiro Hotta. (2019). "Cell Image Segmentation by Pix2pix Using Multiple Different Discriminators." IEEE ISBI 2019. (Poster)

Talks

Conference Proceeding talk 3 on Relevant Topic in Your Field

March 01, 2014

Conference proceedings talk at Testing Institute of America 2014 Annual Conference, Los Angeles, CA, USA

Talk 2 on Relevant Topic in Your Field

February 01, 2014

Talk at London School of Testing, London, UK

Tutorial 1 on Relevant Topic in Your Field

March 01, 2013

Tutorial at UC-Berkeley Institute for Testing Science, Berkeley, CA, USA

Talk 1 on Relevant Topic in Your Field

March 01, 2012

Talk at UC San Francisco, Department of Testing, San Francisco, CA, USA

Teaching

Teaching experience 2

Teaching experience 1

Service and leadership

• Currently signed in to 43 different slack teams