Scholar
Masanori Suganuma
Google Scholar ID: NpWGfwgAAAAJ
Sakana AI
Citations & Impact
Citations
1,988
H-index
17
i10-index
19
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 2025, 'Rethinking Open-Set Object Detection: Issues, A New Formulation, and Taxonomy', International Journal of Computer Vision
- 2025, 'Self-Supervised Learning of Intertwined Content and Positional Features for Object Detection', ICML
- 2025, 'MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval', IJCAI
- 2024, 'Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction', IEEE Transactions on Intelligent Vehicles
- 2024, 'SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers', WACV
- 2024, 'Contextual Affinity Distillation for Image Anomaly Detection', WACV
- 2023, 'Symmetry-aware Neural Architecture for Embodied Visual Navigation', IJCV
- 2023, 'Unsupervised domain adaptation for semantic segmentation via cross-region alignment', CVIU
- 2023, 'Accurate Single-Image Defocus Deblurring Based on Improved Integration with Defocus Map Estimation', ICIP
- 2022, 'Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning', NeurIPS
- 2022, 'GRIT: Faster and Better Image-captioning Transformer Using Dual Visual Features', ECCV
- 2021, 'Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes', ICCV
- 2021, 'Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks', IJCAI
- 2021, 'Hyperparameter-Free Out-of-Distribution Detection Using Cosine Similarity', ACCV
- 2020, 'Evolution of Deep Convolutional Neural Networks Using Cartesian Genetic Programming', Evolutionary Computation
- 2020, 'Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs', ECCV
- 2020, 'Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors', WACV
- 2019, 'Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions', CVPR
- 2019, 'Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration', CVPR
Research Experience
- 2024.8 - Present: Research Scientist at Sakana AI (Cross appointment with Tohoku University from 2024.8 to 2025.1)
- 2021.11 - 2025.1: Visiting Researcher at RIKEN AIP
- 2018.10 - 2025.1: Assistant Professor at Tohoku University (Cross appointment with RIKEN AIP from 2017.10 to 2021.9)
- 2017.10 - 2021.9: Researcher at RIKEN AIP (Cross appointment with Tohoku University)
- 2015.4 - 2017.9: Research Fellow (DC1) at Japan Society for the Promotion of Science (JSPS)
Background
- A research scientist working at Sakana AI in Tokyo. His research focuses on developing good vision and language models.
Co-authors