| Effective data augmentation with multi-domain learning gans S Yamaguchi, S Kanai, T Eda Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 6566-6574, 2020 | 26 | 2020 |
| Pruning randomly initialized neural networks with iterative randomization D Chijiwa, S Yamaguchi, Y Ida, K Umakoshi, T Inoue Advances in neural information processing systems 34, 4503-4513, 2021 | 22 | 2021 |
| Augmentation device, augmentation method, and augmentation program S Yamaguchi, EDA Takeharu, S Muramatsu US Patent App. 17/271,205, 2021 | 22 | 2021 |
| Image enhanced rotation prediction for self-supervised learning S Yamaguchi, S Kanai, T Shioda, S Takeda International Conference on Image Processing (ICIP), 489-493, 2021 | 18* | 2021 |
| Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks D Chijiwa, S Yamaguchi, A Kumagai, Y Ida Advances in Neural Information Processing Systems 35, 25264-25277, 2022 | 5 | 2022 |
| Covariance-Aware Feature Alignment with Pre-Computed Source Statistics for Test-Time Adaptation to Multiple Image Corruptions K Adachi, SY Yamaguchi, A Kumagai International Conference on Image Processing (ICIP), 800-804, 2023 | 4 | 2023 |
| F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain S Yamaguchi, S Kanai International Conference on Computer Vision (ICCV), 6743-6751, 2021 | 4 | 2021 |
| One-vs-the-rest loss to focus on important samples in adversarial training S Kanai, S Yamaguchi, M Yamada, H Takahashi, K Ohno, Y Ida International Conference on Machine Learning (ICML), 15669-15695, 2023 | 3 | 2023 |
| Constraining logits by bounded function for adversarial robustness S Kanai, M Yamada, S Yamaguchi, H Takahashi, Y Ida 2021 International Joint Conference on Neural Networks (IJCNN), 1-8, 2021 | 3 | 2021 |
| Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff S Suzuki, S Yamaguchi, S Takeda, S Kanai, N Makishima, A Ando, ... International Conference on Computer Vision (ICCV), 4390-4401, 2023 | 2 | 2023 |
| Revisiting permutation symmetry for merging models between different datasets M Yamada, T Yamashita, S Yamaguchi, D Chijiwa arXiv preprint arXiv:2306.05641, 2023 | 1 | 2023 |
| Transfer Learning with Pre-trained Conditional Generative Models S Yamaguchi, S Kanai, A Kumagai, D Chijiwa, H Kashima arXiv preprint arXiv:2204.12833, 2022 | 1 | 2022 |
| XML schema validation using parsing expression grammars K Kuramitsu, S Yamaguchi PeerJ PrePrints, 2015 | 1 | 2015 |
| Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switching S Enomoto, N Hasegawa, K Adachi, T Sasaki, S Yamaguchi, S Suzuki, ... arXiv preprint arXiv:2403.17423, 2024 | | 2024 |
| Test-time Similarity Modification for Person Re-identification toward Temporal Distribution Shift K Adachi, S Enomoto, T Sasaki, S Yamaguchi arXiv preprint arXiv:2403.14114, 2024 | | 2024 |
| Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks S Yamaguchi, S Kanai, K Adachi, D Chijiwa arXiv preprint arXiv:2403.10097, 2024 | | 2024 |
| On the Limitation of Diffusion Models for Synthesizing Training Datasets S Yamaguchi, T Fukuda NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI, 2023 | | 2023 |
| Training device, training method and training program S Yamaguchi, S Kanai US Patent App. 18/021,810, 2023 | | 2023 |
| Supplementary Materials of “Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples” S Yamaguchi Proceedings of Machine Learning Research 222 (2023), 2023 | | 2023 |
| Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples S Yamaguchi Asian Conference on Machine Learning, 1510-1525, 2023 | | 2023 |
Sekitoshi KanaiNTTVerified email at hco.ntt.co.jp
