Preprint

1. Korawat Charoenpitaks, Van-Quang Nguyen, Masanori Suganuma, Masahiro Takahashi, Ryoma Niihara, Takayuki Okatani: Visual Abductive Reasoning Meets Driving Hazard Prediction: Problem Formulation and Dataset, arXiv:2310.04671, 2023 [arXiv]

2. Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani: More Practical Scenario of Open-set Object Detection: Open at Category Level and Closed at Super-category Level, arXiv:2207.09775, 2022 [arXiv]

3. Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani: GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features, arXiv:2207.09666, 2022 (Accepted to ECCV 2022) [arXiv]

4. Zhijie Wang, Masanori Suganuma, Takayuki Okatani: Rethinking Unsupervised Domain Adaptation for Semantic Segmentation, arXiv:2207.00067, 2022 [arXiv]

5. Qian Ye, Masanori Suganuma, Takayuki Okatani: Single-image Defocus Deblurring by Integration of Defocus Map Prediction Tracing the Inverse Problem Computation, arXiv:2207.03047, 2022 [arXiv]

6. Qian Ye, Masanori Suganuma, Jun Xiao, Takayuki Okatani: Learning Regularized Multi-Scale Feature Flow for High Dynamic Range Imaging, arXiv:2207.02539, 2022 [arXiv]

7. Zhijie Wang, Masanori Suganuma, Takayuki Okatani: Improved Few-shot Segmentation by Redefinition of the Roles of Multi-level CNN Features, arXiv:2109.06432, 2021 [arXiv]

8. Zhijie Wang, Xing Liu, Masanori Suganuma, Takayuki Okatani: Cross-Region Domain Adaptation for Class-level Alignment, arXiv:2109.06422, 2021 [arXiv]

9. Wenzheng Song, Masanori Suganuma, Xing Liu, Noriyuki Shimobayashi, Daisuke Maruta, Takayuki Okatani: Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes, arXiv:2109.03585, 2021 (Accepted to ICCV 2021) [arXiv]

10. Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani: Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks, arXiv:2106.00596, 2021 (Accepted to IJCAI 2021) [arXiv]

11. Rito Murase, Masanori Suganuma, Takayuki Okatani: How Can CNNs Use Image Position for Segmentation?, arXiv:2005.03463, 2020 [arXiv]

12. Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani: Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs, arXiv:1911.11390, 2019 (Accepted to ECCV 2020) [arXiv]

13. Engkarat Techapanurak, Masanori Suganuma, Takayuki Okatani: Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity, arXiv:1905.10628, 2019 (Accepted to ACCV 2020) [arXiv]

14. Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani: Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors, arXiv:1910.09212, 2019 (Accepted to WACV 2020) [arXiv]

15. Xing Liu, Masanori Suganuma, Takayuki Okatani:  Restoring Images with Unknown Degradation Factors by Recurrent Use of a Multi-branch Network, arXiv:1907.04508, 2019 [arXiv]

16. Masanori Suganuma, Xing Liu, Takayuki Okatani: Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions, arXiv:1812.00733, 2018 (Accepted to CVPR 2019) [arXiv] [code]

17. Masanori Suganuma, Mete Ozay, Takayuki Okatani: Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search, arXiv:1803.00370, 2018 (Accepted to ICML 2018) [arXiv] [code] 

Journal Papers

1. Shuang Liu, Masanori Suganuma, Takayuki Okatani: Symmetry-aware Neural Architecture for Embodied Visual Navigation, International Journal of Computer Vision (IJCV), 2023

2. Zhijie Wang, Xing Liu, Masanori Suganuma, and Takayuki Okatani: Unsupervised domain adaptation for semantic segmentation via cross-region alignment, Computer Vision and Image Understanding (CVIU), 2023

3. Hiroki Kurita, Masanori Suganuma, Yinli Wang, Fumio Narita: k‐Means Clustering for Prediction of Tensile Properties in Carbon Fiber‐Reinforced Polymer Composites, Advanced Engineering Materials 24 (5), 2022

4. Masanori Suganuma, Masayuki Kobayashi, Shinichi Shirakawa, Tomoharu Nagao: Evolution of Deep Convolutional Neural Networks Using Cartesian Genetic Programming, Evolutionary Computation 28(1):141-163, MIT Press, 2020

5. Masayuki Kobayashi, Masanori Suganuma, Tomoharu Nagao: A Generative Model Approach for Visualising, International Journal of Computational Intelligence Studies, 2018

6. Takahito Hata, Masanori Suganuma, Tomoharu Nagao: Controlling an Autonomous Agent for Exploring Unknown Environments using Switching Prelearned Modules（既学習モジュールの切替による未知環境探索エージェントの行動制御）, Electronics and Communications in Japan, 2018

7. 畠崇人，菅沼雅徳，長尾智晴：既学習モジュールの切替による未知環境探索エージェントの行動制御，電気学会論文誌C，Vol.138, No.2, pp.157-164, 2017

8. 小林雅幸，菅沼雅徳，崎津実穂，長尾智晴：進化的条件判断ネットワークにおける画像分類過程の可視化，進化計算学会論文誌, Vol.7, No.3, pp.65-76, 2016

9. 菅沼雅徳，土屋大樹，白川真一，長尾智晴：遺伝的プログラミングを用いた階層的な特徴構築による画像分類，情報処理学会論文誌：数理モデル化と応用(TOM), Vol.9, No.3, pp.44-53, 2016 [PDF] 1

10. 工藤理人，菅沼雅徳，長尾智晴：ユニットの冗長化による耐故障性を考慮した進化型ニューラルネットワーク，情報処理学会論文誌：数理モデル化と応用(TOM), Vol.9, No.3, pp.54-60, 2016

11. 菅沼雅徳，長尾智晴：異常検知のための自己組織化モデルとその監視映像への適用，情報処理学会論文誌：数理モデル化と応用(TOM), Vol.9, No.1, pp.23-32, 2016 [PDF] 1

12. 崎津実穂，菅沼雅徳，土屋大樹，長尾智晴：決定木及び決定ネットワークによる画像分類過程の説明文の自動生成，情報処理学会論文誌：数理モデル化と応用(TOM), Vol.9, No.1, pp.43-52, 2016

13. 菅沼雅徳，長尾智晴，田村学，村垣善浩，伊関洋：覚醒下脳腫瘍摘出術における皮質マッピング動画像記録の電気刺激位置の自動検出，Medical Imaging Technology, Vol.32, No.4, pp.272-281, 2014 [PDF]

Refereed Conferences (査読付き国際会議論文)

1. Lu Xiangyong, Masanori Suganuma, Takayuki Okatani: SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers, IEEE Winter Conference on Applications of Computer Vision (WACV), 2024

2. Zhang Jie, Masanori Suganuma, Takayuki Okatani: Contextual Affinity Distillation for Image Anomaly Detection, IEEE Winter Conference on Applications of Computer Vision (WACV), 2024

3. Qian Ye, Masanori Suganuma, and Takayuki Okatani: Accurate Single-Image Defocus Deblurring Based on Improved Integration with Defocus Map Estimation, IEEE Conference on Image Processing (ICIP), 2023

4. Kang-Jun Liu, Masanori Suganuma, Takayuki Okatani: Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning, Neural Information Processing Systems (NeurIPS), 2022 [PDF]

5. Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani: GRIT: Faster and Better Image-captioning Transformer Using Dual Visual Features, European Conference on Computer Vision (ECCV), 2022 [PDF] [arXiv]

6. Wenzheng Song, Masanori Suganuma, Xing Liu, Noriyuki Shimobayashi, Daisuke Maruta, Takayuki Okatani: Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes, International Conference on Computer Vision (ICCV), 2021 [PDF] [arXiv]

7. Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani: Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks, International Joint Conference on Artificial Intelligence (IJCAI), 2021 [PDF] [arXiv]

8. Engkarat Techapanurak, Masanori Suganuma, Takayuki Okatani: Hyperparameter-Free Out-of-Distribution Detection Using Cosine Similarity, Asian Conference on Computer Vision (ACCV), 2020 [PDF] [arXiv]

9. Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani: Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs, European Conference on Computer Vision (ECCV), 2020 [PDF] [arXiv]

10. Yoshihiro Hirohashi, Kenichi Narioka, Masanori Suganuma, Xing Liu,  Yukimasa Tamatsu, Takayuki Okatani: Removal of Image Obstacles for Vehicle-mounted Surrounding Monitoring Cameras by Real-time Video Inpainting, IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2020 [PDF]

11. Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani: Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors, IEEE Winter Conference on Applications of Computer Vision (WACV), 2020 [PDF][arXiv]

12. Masanori Suganuma, Xing Liu, Takayuki Okatani: Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 [PDF] [arXiv] [code] [poster]

13. Xing Liu, Masanori Suganuma, Zhun Sun, Takayuki Okatani: Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 [PDF] [arXiv] [code]

14. Takayuki Okatani, Xing Liu, Masanori Suganuma: Improving Generalization Ability of Deep Neural Networks for Visual Recognition Tasks, International Workshop on Computational Color Imaging (CCIW), Chiba, Japan, 27-29, March, 2019

15. Masanori Suganuma, Mete Ozay, Takayuki Okatani: Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search, The 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 10-15 July, 2018 [PDF] [arXiv] [code (PyTorch)] 

16. Masanori Suganuma, Shinichi Shirakawa, Tomoharu Nagao: A genetic programming approach to designing convolutional neural network architectures, The Sister Conference Best Paper Track at the 27th International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden, 13-19 July, 2018 [PDF] [code (Chainer)] [code (PyTorch)]

17. Kobayashi Masayuki, Masanori Suganuma, Tomoharu Nagao: Generative Adversarial Network for Visualizing Convolutional Network, IEEE 10th International Workshop on Computational Intelligence and Applications (IWCIA), Hiroshima, Japan, 11-12 November, 2017

18. Chiaki Hirayama, Toshiya Watanabe, Shinji Kawabata, Masanori Suganuma, Tomoharu Nagao: Acquiring grasp strategies for a multifingered robot hand using evolutionary algorithms, the 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Banff, Canada, 5-8 October, 2017

19. Masanori Suganuma, Shinichi Shirakawa, Tomoharu Nagao: A genetic programming approach to designing convolutional neural network architectures, The Genetic and Evolutionary Computation Conference (GECCO), Berlin, Germany, 15-19 July, 2017 (Best Paper Award) [PDF] [arXiv] [code (Chainer)] [code (PyTorch)] 

20. Masanori Suganuma, Daiki Tsuchiya, Shinichi Shirakawa, Tomoharu Nagao: Hierarchical feature construction for image classification using genetic programming, IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp.1423-1428, Budapest, Hungary, 9-12 October, 2016. DOI: 10.1109/SMC.2016.7844436 [PDF] [IEEE Xplore] 2

21. Masanori Suganuma, Toshihiko Nishimura, Tomoharu Nagao, Hiroshi Iseki, Yoshihiro Muragaki, Manabu Tamura, Shinji Minami: Automatic detection of electrical stimulation timing in operation videos of cortical mapping in awake brain surgery, International Conference on Medical Image Computation and Computer Assisted Intervention (MICCAI) Workshop on Modeling and Monitoring of Computer Assisted Interventions (M2CAI), pp.37-46, Nagoya, Japan, 22 September, 2013

22. Toshihiko Nishimura, Masanori Suganuma, Tomoharu Nagao, Hiroshi Iseki, Yoshihiro Muragaki, Manabu Tamura, Shinji Minami: Intraoperative voice classification for analysis of cortical mapping during awake surgery, International Conference on Medical Image Computation and Computer Assisted Intervention (MICCAI) Workshop on Modeling and Monitoring of Computer Assisted Interventions (M2CAI), pp.27-36, Nagoya, Japan, 22 September, 2013

23. Masanori Suganuma, Tomoharu Nagao: Detection of electrical stimulation position in recorded surgery videos of cortical mapping in awake brain surgery, IEEE 6th International Workshop on Computational Intelligence and Applications (IWCIA), pp.131-136, Hiroshima, Japan, 13 July, 2013. DOI: 10.1109/IWCIA.2013.6624800 [IEEE Xplore]

Invited Talk (招待講演)

1. 菅沼雅徳：進化計算と深層学習の融合，IEEE SMC Hiroshima Chapter 若手研究会,  2019

2. 菅沼雅徳：深層学習の基礎と応用，生態学会大会，2018

Workshop

1. Masanori Suganuma, Takayuki Okatani: Designing Convolutional Neural Network Architectures for Image Restoration, UK-Japan robotics and AI research collaboration workshops, 2019

Books

1. 菅沼 雅徳：「深層学習による画像認識の基礎」（オーム社）[Amazon] [オーム社HP]．本書の正誤表はこちら．

2. Masanori Suganuma, Shinichi Shirakawa, and Tomoharu Nagao: Designing Convolutional Neural Network Architectures Using Cartesian Genetic Programming, In H. Iba and N. Noman (eds), Deep Neural Evolution –Deep Learning with Evolutionary Computation, chapter 7, pp. 185-208, Springer, 2020 [link]

Domestic Conferences (国内発表)

1. 菅沼雅徳：視覚言語融合タスクにおけるTransformerの自動構造探索，人工知能学会全国大会，2022

2. 財満誠，劉星，菅沼雅徳，岡谷貴之:NeRFによる新規視点画像生成における形状推定精度の影響，MIRU，2021

3. 栗原尭大，菅沼雅徳，劉星，岡谷貴之：単眼深度推定における事前学習の効果の分析，MIRU，2021

4. 菅沼雅徳，劉星，岡谷貴之: 複合ノイズ下における画像復元のための適応的な演算選択，数学パワーが世界を変える（CREST，さきがけ，AIMaP合同シンポジウム）, 2020

5. 菅沼雅徳，岡谷貴之: Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search，数学パワーが世界を変える（CREST，さきがけ，AIMaP合同シンポジウム）, 2019

6. 菅沼雅徳，白川真一，長尾智晴：畳み込みニューラルネットワークの構造最適化手法の調査と遺伝的プログラミングによるアプローチ，電気学会 電子・情報・システム部門大会，2017

7. 小林雅幸，菅沼雅徳，崎津実穂，長尾智晴：進化的条件判断ネットワークにおける画像分類過程の可視化，第11回進化計算学会研究会，2016

8. 菅沼雅徳，土屋大樹，白川真一，長尾智晴：遺伝的プログラミングを用いた階層的な特徴構築による画像分類，情報処理学会研究報告 第108回 数理モデル化と問題解決（MPS）研究会，Vol. 2016-MPS-108, No. 4, pp. 1-6, 2016

9. 工藤理人，菅沼雅徳，長尾智晴：ユニットの冗長化による耐故障性を考慮した進化型ニューラルネットワーク，情報処理学会研究報告 第108回 数理モデル化と問題解決（MPS）研究会，2016

10. 畠崇人，菅沼雅徳，長尾智晴：モジュール切替による未知環境に適応可能な探索エージェントの行動制御，情報処理学会研究報告 第108回 数理モデル化と問題解決（MPS）研究会，2016

11. 小林雅幸，菅沼雅徳，崎津実穂，長尾智晴：進化的条件判断ネットワークの画像分類過程の可視化，情報処理学会研究報告 第108回 数理モデル化と問題解決（MPS）研究会，Vol. 2016-MPS-108, No. 1, pp. 1-7, 2016

12. 前原良美，菅沼雅徳，長尾智晴：三次元空間把握のための音楽化手法，情報処理学会研究報告 第13回 デジタルコンテンツクリエーション(DCC)研究会，Vol. 2016-DCC-13, No. 3, pp. 1-7, 2016

13. 菅沼雅徳，長尾智晴：環境に応じた侵入物体検知を行う監視カメラ，STARCフォーラム2015, 2015

14. 菅沼雅徳，長尾智晴：異常検知のための自己組織化ネットワークとその監視映像への適用，情報処理学会研究報告 第105回 数理モデル化と問題解決（MPS）研究会，Vol. 2015-MPS-105, No. 5, pp. 1-6, 2015

15. 崎津実穂，菅沼雅徳，土屋大樹，長尾智晴：決定木及び決定ネットワークによる画像分類過程の説明文の自動生成，情報処理学会研究報告 第105回 数理モデル化と問題解決（MPS）研究会，Vol. 2015-MPS-105, No. 4, pp. 1-6, 2015

16. 菅沼雅徳，長尾智晴：脳の記憶構造に着目した監視カメラからの異常検知，STARCシンポジウム2015, 2015

17. 菅沼雅徳，長尾智晴，田村学，村垣善浩，伊関洋：覚醒下脳腫瘍摘出術の動画像記録における電気刺激位置の自動検出，電子情報通信学会総合大会，D-7-11，2014

18. 西村俊彦，菅沼雅徳，長尾智晴：覚醒下脳腫瘍摘出術の動画像記録に対する自動解析，情報処理学会第75回全国大会，3ZG-5，2013

______________________________________________________________________________________

1. 本論文は著作権者である情報処理学会の許可のもとに掲載しています．ご利用の際は著作権法に従ってください．

2. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

______________________________________________________________________________________