Masanori Suganuma
Research Scientist
Sakana AI
I'm a research scientist working at Sakana AI in Tokyo. My research focuses on developing good vision and language models.
Experience
Research Scientist — Sakana AI
Cross appointment with Tohoku University from 2024.8 to 2025.1
Visiting Researcher — RIKEN AIP
Assistant Professor — Tohoku University
Cross appointment with RIKEN AIP from 2017.10 to 2021.9
Researcher — RIKEN AIP
Cross appointment with Tohoku University
Research Fellow (DC1) — Japan Society for the Promotion of Science (JSPS)
Publications
IEEE Transactions on Intelligent Vehicles 2024
Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction
Korawat Charoenpitaks, Van-Quang Nguyen, Masanori Suganuma, Masahiro Takahashi, Ryoma Niihara, Takayuki Okatani
WACV 2024
SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers
Lu Xiangyong, Masanori Suganuma, Takayuki Okatani
WACV 2024
Contextual Affinity Distillation for Image Anomaly Detection
Zhang Jie, Masanori Suganuma, Takayuki Okatani
IJCV 2023
Symmetry-aware Neural Architecture for Embodied Visual Navigation
Shuang Liu, Masanori Suganuma, Takayuki Okatani
CVIU 2023
Unsupervised domain adaptation for semantic segmentation via cross-region alignment
Zhijie Wang, Xing Liu, Masanori Suganuma, Takayuki Okatani
ICIP 2023
Accurate Single-Image Defocus Deblurring Based on Improved Integration with Defocus Map Estimation
Qian Ye, Masanori Suganuma, Takayuki Okatani
NeurIPS 2022
Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning
Kang-Jun Liu, Masanori Suganuma, Takayuki Okatani
ECCV 2022
GRIT: Faster and Better Image-captioning Transformer Using Dual Visual Features
Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani
ICCV 2021
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes
Wenzheng Song, Masanori Suganuma, Xing Liu, Noriyuki Shimobayashi, Daisuke Maruta, Takayuki Okatani
IJCAI 2021
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks
Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani
ACCV 2021
Hyperparameter-Free Out-of-Distribution Detection Using Cosine Similarity
Engkarat Techapanurak, Masanori Suganuma, Takayuki Okatani
Evolutionary Computation 2020
Evolution of Deep Convolutional Neural Networks Using Cartesian Genetic Programming
Masanori Suganuma, Masayuki Kobayashi, Shinichi Shirakawa, Tomoharu Nagao
ECCV 2020
Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs
Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani
WACV 2020
Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors
Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
CVPR 2019
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
Xing Liu, Masanori Suganuma, Zhun Sun, Takayuki Okatani
GECCO 2017
🏆 Best Paper Award
A genetic programming approach to designing convolutional neural network architectures
Masanori Suganuma, Shinichi Shirakawa, Tomoharu Nagao
Education
Yokohama National University
Ph.D. in Engineering (finished in 2.5 years)
Yokohama National University
M.S. in Engineering
Yokohama National University
dropout for grade-skipping