Suganuma Masanori 菅沼雅徳

Researcher Number	00815813
Other IDs
Affiliation (based on the past Project Information) *help	2019 – 2024: 東北大学, 情報科学研究科, 助教
Review Section/Research Field	Principal Investigator Basic Section 61010:Perceptual information processing-related Except Principal Investigator Medium-sized Section 61:Human informatics and related fields / Transformative Research Areas, Section (IV)
Keywords	Principal Investigator ニューラルネットワーク / 構造自動設計 / 自動構造探索 / 画像修復 / 画像劣化 / 画像分類 / ドメインシフト / ニューラル構造探索 / 画像認識 / 深層学習 … More Except Principal Investigator … More 人工知能 / コンピュータビジョン / 深層学習 / 画像理解 / 自然言語 / マルチモーダルAI / 対話型AI / 車載カメラ画像 / 知識獲得 / 自然言語処理 / 質感認識 / 画像と言語 / 言語モデル / 質感 / 構造自動設計 / ディープラーニング / 画像処理 / 画像認識 / cv / ニューラルネットワーク Less

専門知に基づいて画像を理解し説明する対話型AIの実現
- Principal Investigator
  
  岡谷貴之
- Project Period (FY)
  2023 – 2026
- Research Category
  
  Grant-in-Aid for Scientific Research (A)
- Review Section
  
  Medium-sized Section 61:Human informatics and related fields
- Research Institution
  Tohoku University
Designing deep network architectures to solve domain shiftPrincipal Investigator
- Principal Investigator
  
  Suganuma Masanori
- Project Period (FY)
  2021 – 2023
- Research Category
  
  Grant-in-Aid for Early-Career Scientists
- Review Section
  
  Basic Section 61010:Perceptual information processing-related
- Research Institution
  Tohoku University
深奥質感のマルチモーダル深層モデルの確立
- Principal Investigator
  
  岡谷貴之
- Project Period (FY)
  2020 – 2024
- Research Category
  
  Grant-in-Aid for Transformative Research Areas (A)
- Review Section
  
  Transformative Research Areas, Section (IV)
- Research Institution
  Tohoku University
Developing a Design Methodology of Deep Neural Networks to Accelerate Paradigm Shit Brought by Deep Learning
- Principal Investigator
  
  Okatani Takayuki
- Project Period (FY)
  2019 – 2022
- Research Category
  
  Grant-in-Aid for Scientific Research (A)
- Review Section
  
  Medium-sized Section 61:Human informatics and related fields
- Research Institution
  Tohoku University

All 2024 2023 2022 2021 2020 2019

All Journal Article

[Journal Article] Contextual Affinity Distillation for Image Anomaly Detection2024
- Author(s)
  Zhang Jie、Suganuma Masanori、Okatani Takayuki
- Journal Title
  
  Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision
  
  Volume: - Pages: 148-157
- DOI
  10.1109/wacv57701.2024.00022
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23H00482
[Journal Article] SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers2024
- Author(s)
  Lu Xiangyong、Suganuma Masanori、Okatani Takayuki
- Journal Title
  
  Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision
  
  Volume: - Pages: 1112-1122
- DOI
  10.1109/wacv57701.2024.00116
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23H00482
[Journal Article] That’s BAD: blind anomaly detection by implicit local feature clustering2024
- Author(s)
  Zhang Jie、Suganuma Masanori、Okatani Takayuki
- Journal Title
  
  Machine Vision and Applications
  
  Volume: 35 Issue: 2
- DOI
  10.1007/s00138-024-01511-9
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23H00482
[Journal Article] Symmetry-aware Neural Architecture for Embodied Visual Navigation2023
- Author(s)
  Liu Shuang、Suganuma Masanori、Okatani Takayuki
- Journal Title
  
  International Journal of Computer Vision
  
  Volume: 132 Issue: 4 Pages: 1091-1107
- DOI
  10.1007/s11263-023-01909-4
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23H00482
[Journal Article] Unsupervised domain adaptation for semantic segmentation via cross-region alignment2023
- Author(s)
  Wang Zhijie、Liu Xing、Suganuma Masanori、Okatani Takayuki
- Journal Title
  
  Computer Vision and Image Understanding
  
  Volume: 234 Pages: 103743-103743
- DOI
  10.1016/j.cviu.2023.103743
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23H00482
[Journal Article] Improving visual question answering for bridge inspection by pre‐training with external data of image?text pairs2023
- Author(s)
  Kunlamai Thannarot、Yamane Tatsuro、Suganuma Masanori、Chun Pang‐Jo、Okatani Takayaki
- Journal Title
  
  Computer-Aided Civil and Infrastructure Engineering
  
  Volume: 39 Issue: 3 Pages: 345-361
- DOI
  10.1111/mice.13086
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23H00482
[Journal Article] Network Pruning and Fine-tuning for Few-shot Industrial Image Anomaly Detection2023
- Author(s)
  Zhang Jie、Suganuma Masanori、Okatani Takayuki
- Journal Title
  
  Proceedings of IEEE International Conference on Industrial Informatics
  
  Volume: - Pages: 1-6
- DOI
  10.1109/indin51400.2023.10218283
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-23H00482
[Journal Article] Accurate Single-Image Defocus Deblurring Based on Improved Integration with Defocus Map Estimation2023
- Author(s)
  Ye Qian、Suganuma Masanori、Okatani Takayuki
- Journal Title
  
  Proceedings of International Conference on Image Processing
  
  Volume: - Pages: 750-754
- DOI
  10.1109/icip49359.2023.10223146
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23H00482
[Journal Article] GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features2022
- Author(s)
  Nguyen Van-Quang, Suganuma Masanori, Okatani Takayuki
- Journal Title
  
  Proceedings of European Conference on Computer Vision
  
  Volume: - Pages: 167-184
- DOI
  10.1007/978-3-031-20059-5_10
- ISBN
  9783031200588, 9783031200595
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PLANNED-20H05952
[Journal Article] Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self- supervised Learning2022
- Author(s)
  Kang-Jun Liu, Masanori Suganuma, Takayuki Okatani
- Journal Title
  
  Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
  
  Volume: - Pages: 19824-19835
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19H01110
[Journal Article] Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning2022
- Author(s)
  Kang-Jun Liu, Masanori Suganuma, Takayuki Okatani
- Journal Title
  
  Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
  
  Volume: - Pages: 19824-19835
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PLANNED-20H05952
[Journal Article] Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes2021
- Author(s)
  Wenzheng Song, Masanori Suganuma, Xing Liu, Noriyuki Shimobayashi, Daisuke Maruta, Takayuki Okatani
- Journal Title
  
  Proceedings of International Conference on Computer Visionツ?2021
  
  Volume: - Pages: 6009-6018
- DOI
  10.1109/iccv48922.2021.00597
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PLANNED-20H05952, KAKENHI-PROJECT-19H01110
[Journal Article] Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks2021
- Author(s)
  Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani
- Journal Title
  
  Proceedings of 30th International Joint Conference on Artificial Intelligence (IJCAI-21)
  
  Volume: - Pages: 923-930
- DOI
  10.24963/ijcai.2021/128
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PLANNED-20H05952, KAKENHI-PROJECT-19H01110
[Journal Article] Hyperparameter-Free Out-of-Distribution Detection Using Cosine Similarity2020
- Author(s)
  Engkarat Techapanurak, Masanori Suganuma, Takayuki Okatani:
- Journal Title
  
  Proceedings of Asian Conference on Computer Vision
  
  Volume: - Pages: 53-69
- DOI
  10.1007/978-3-030-69538-5_4
- ISBN
  9783030695378, 9783030695385
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19H01110
[Journal Article] Efficient Attention Mechanism for Visual Dialog that Can Handle All the Interactions Between Multiple Inputs2020
- Author(s)
  Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani
- Journal Title
  
  Proceedings of European Conference on Computer Vision
  
  Volume: - Pages: 223-240
- DOI
  10.1007/978-3-030-58586-0_14
- ISBN
  9783030585853, 9783030585860
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19H01110
[Journal Article] Removal of Image Obstacles for Vehicle-mounted Surrounding Monitoring Cameras by Real-time Video Inpainting2020
- Author(s)
  Yoshihiro Hirohashi, Kenichi Narioka, Masanori Suganuma, Xing Liu, Yukimasa Tamatsu, Takayuki Okatani
- Journal Title
  
  Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops
  
  Volume: - Pages: 857-866
- DOI
  10.1109/cvprw50498.2020.00115
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19H01110
[Journal Article] Joint Learning of Multiple Image Restoration Tasks2020
- Author(s)
  Xing Liu, Masanori Suganuma, Takayuki Okatani
- Journal Title
  
  arXiv.org
  
  Volume: - Pages: 1-10
- Open Access
- Data Source
  KAKENHI-PROJECT-19H01110
[Journal Article] Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors2020
- Author(s)
  Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
- Journal Title
  
  Proceedings of IEEE Winter Conference on Applications of Computer Vision
  
  Volume: - Pages: 1399-1407
- DOI
  10.1109/wacv45572.2020.9093553
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19H01110
[Journal Article] Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions2019
- Author(s)
  Suganuma Masanori、Liu Xing、Okatani Takayuki
- Journal Title
  
  Proceedings of IEEE Computer Vision and Pattern Recognition
  
  Volume: - Pages: 9039-9048
- DOI
  10.1109/cvpr.2019.00925
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19H01110, KAKENHI-PLANNED-15H05919
[Journal Article] Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration2019
- Author(s)
  Liu Xing、Suganuma Masanori、Sun Zhun、Okatani Takayuki
- Journal Title
  
  Proceedings of IEEE Computer Vision and Pattern Recognition
  
  Volume: - Pages: 7007-7016
- DOI
  10.1109/cvpr.2019.00717
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19H01110, KAKENHI-PLANNED-15H05919

1. Okatani Takayuki (00312637)

# of Collaborated Projects: 3 results

# of Collaborated Products: 20 results
2. 鈴木潤 (80396150)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
3. 劉星 (60870095)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results

Suganuma Masanori 菅沼 雅徳

Research Projects

Research Products

Co-Researchers

専門知に基づいて画像を理解し説明する対話型AIの実現

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Designing deep network architectures to solve domain shiftPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

深奥質感のマルチモーダル深層モデルの確立

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Developing a Design Methodology of Deep Neural Networks to Accelerate Paradigm Shit Brought by Deep Learning

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

[Journal Article] Contextual Affinity Distillation for Image Anomaly Detection2024

Author(s)

Journal Title

DOI

Data Source

[Journal Article] SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers2024

Author(s)

Journal Title

DOI

Data Source

[Journal Article] That’s BAD: blind anomaly detection by implicit local feature clustering2024

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Symmetry-aware Neural Architecture for Embodied Visual Navigation2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Unsupervised domain adaptation for semantic segmentation via cross-region alignment2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Improving visual question answering for bridge inspection by pre‐training with external data of image?text pairs2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Network Pruning and Fine-tuning for Few-shot Industrial Image Anomaly Detection2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Accurate Single-Image Defocus Deblurring Based on Improved Integration with Defocus Map Estimation2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features2022

Author(s)

Journal Title

DOI

ISBN

Data Source

[Journal Article] Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self- supervised Learning2022

Author(s)

Journal Title

Data Source

[Journal Article] Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning2022

Author(s)

Suganuma Masanori 菅沼雅徳