| Virtual adversarial training: a regularization method for supervised and semi-supervised learning T Miyato, S Maeda, M Koyama, S Ishii IEEE transactions on pattern analysis and machine intelligence 41 (8), 1979-1993, 2018 | 1585 | 2018 |
| Distributional smoothing with virtual adversarial training T Miyato, S Maeda, M Koyama, K Nakae, S Ishii arXiv preprint arXiv:1507.00677, 2015 | 472 | 2015 |
| Robustness to adversarial perturbations in learning from incomplete data A Najafi, S Maeda, M Koyama, T Miyato Advances in Neural Information Processing Systems, 5541-5551, 2019 | 75 | 2019 |
| An occlusion-aware particle filter tracker to handle complex and persistent occlusions K Meshgi, S Maeda, S Oba, H Skibbe, Y Li, S Ishii Computer Vision and Image Understanding 150, 81-94, 2016 | 71 | 2016 |
| Superresolution with compound Markov random fields via the variational EM algorithm A Kanemura, S Maeda, S Ishii Neural Networks 22 (7), 1025-1034, 2009 | 65 | 2009 |
| Semaphorin 3A induces Ca V 2.3 channel-dependent conversion of axons to dendrites M Nishiyama, K Togashi, MJ Von Schimmelmann, CS Lim, S Maeda, ... Nature cell biology 13 (6), 676-685, 2011 | 49 | 2011 |
| A Bayesian encourages dropout S Maeda arXiv preprint arXiv:1412.7003, 2014 | 48 | 2014 |
| DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback R Arakawa, S Kobayashi, Y Unno, Y Tsuboi, S Maeda arXiv preprint arXiv:1810.11748, 2018 | 43 | 2018 |
| Gaussian process regression for rendering music performance K Teramura, H Okuma, Y Taniguchi, S Makimoto, S Maeda Proc. ICMPC, 167-172, 2008 | 41 | 2008 |
| Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks K Hayashi, T Yamaguchi, Y Sugawara, S Maeda Advances in Neural Information Processing Systems, 5552-5562, 2019 | 33 | 2019 |
| Clipped action policy gradient Y Fujita, S Maeda International Conference on Machine Learning, 1597-1606, 2018 | 30 | 2018 |
| Markov and semi-Markov switching of source appearances for nonstationary independent component analysis J Hirayama, S Maeda, S Ishii IEEE transactions on neural networks 18 (5), 1326-1342, 2007 | 23 | 2007 |
| Neural multi-scale image compression KM Nakanishi, S Maeda, T Miyato, D Okanohara Asian Conference on Computer Vision, 718-732, 2018 | 22 | 2018 |
| Graph warp module: an auxiliary module for boosting the power of graph neural networks K Ishiguro, S Maeda, M Koyama arXiv preprint arXiv:1902.01020, 2019 | 21 | 2019 |
| Maximum a posteriori X-ray computed tomography using graph cuts S Maeda, W Fukuda, A Kanemura, S Ishii Journal of Physics: Conference Series 233 (1), 012023, 2010 | 18 | 2010 |
| Edge-preserving Bayesian image superresolution based on compound Markov random fields A Kanemura, S Maeda, S Ishii International Conference on Artificial Neural Networks, 611-620, 2007 | 17 | 2007 |
| Rebuilding factorized information criterion: Asymptotically accurate marginal likelihood K Hayashi, S Maeda, R Fujimaki International Conference on Machine Learning, 1358-1366, 2015 | 15 | 2015 |
| Generalized TD learning T Ueno, S Maeda, M Kawanabe, S Ishii Journal of Machine Learning Research 12 (Jun), 1977-2020, 2011 | 15 | 2011 |
| Hyperparameter estimation in Bayesian image superresolution with a compound Markov random field prior A Kanemura, S Maeda, S Ishii 2007 IEEE Workshop on Machine Learning for Signal Processing, 181-186, 2007 | 14 | 2007 |
| Efficient Monte Carlo image analysis for the location of vascular entity H Skibbe, M Reisert, S Maeda, M Koyama, S Oba, K Ito, S Ishii IEEE Transactions on medical imaging 34 (2), 628-643, 2014 | 12 | 2014 |
