Shin'ya Yamaguchi

54 papers A* 12A 1B 6C 3Journal 31Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models. AAAI Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Taiga Yamane, Naoki Makishima, Naotaka Kawata, Mana Ihori, Tomohiro Tanaka, Shota Orihashi, Ryo Masumura
2026	J	`jnl`	MultiModal Fine-tuning with Synthetic Captions. CoRR Shohei Enomoto, Shin'ya Yamaguchi
2026	J	`jnl`	Parallel In-context Learning for Large Vision Language Models. CoRR Shin'ya Yamaguchi, Daiki Chijiwa, Tamao Sakao, Taku Hasegawa
2025	J	`jnl`	Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models. CoRR Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Taiga Yamane, Naoki Makishima, Naotaka Kawata, Mana Ihori, Tomohiro Tanaka, Shota Orihashi, Ryo Masumura
2025	B	`conf`	Evaluation of Time-Series Training Dataset through Lens of Spectrum of Deep State Space Models. IJCNN Sekitoshi Kanai, Yasutoshi Ida, Kazuki Adachi, Mihiro Uchida, Tsukasa Yoshida, Shin'ya Yamaguchi
2025	A*	`conf`	Explanation Bottleneck Models. AAAI Shin'ya Yamaguchi, Kosuke Nishida
2025	J	`jnl`	Lossless Vocabulary Reduction for Auto-Regressive Language Models. CoRR Daiki Chijiwa, Taku Hasegawa, Kyosuke Nishida, Shin'ya Yamaguchi, Tomoya Ohba, Tamao Sakao, Susumu Takeuchi
2025	A*	`conf`	Post-pre-training for Modality Alignment in Vision-Language Foundation Models. CVPR Shin'ya Yamaguchi, Dewei Feng, Sekitoshi Kanai, Kazuki Adachi, Daiki Chijiwa
2025	J	`jnl`	Post-pre-training for Modality Alignment in Vision-Language Foundation Models. CoRR Shin'ya Yamaguchi, Dewei Feng, Sekitoshi Kanai, Kazuki Adachi, Daiki Chijiwa
2025	J	`jnl`	Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought. CoRR Shin'ya Yamaguchi, Kosuke Nishida, Daiki Chijiwa
2025	A*	`conf`	Test-time Adaptation for Regression by Subspace Alignment. ICLR Kazuki Adachi, Shin'ya Yamaguchi, Atsutoshi Kumagai, Tomoki Hamagami
2025	J	`jnl`	Transfer learning with pre-trained conditional generative models. Mach. Learn. Shin'ya Yamaguchi, Sekitoshi Kanai, Atsutoshi Kumagai, Daiki Chijiwa, Hisashi Kashima
2025	J	`jnl`	Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption. CoRR Kazuki Adachi, Shin'ya Yamaguchi, Tomoki Hamagami
2025	J	`jnl`	Zero-shot Concept Bottleneck Models. CoRR Shin'ya Yamaguchi, Kosuke Nishida, Daiki Chijiwa, Yasutoshi Ida
2024	A*	`conf`	Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks. CVPR Shin'ya Yamaguchi, Sekitoshi Kanai, Kazuki Adachi, Daiki Chijiwa
2024	J	`jnl`	Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks. CoRR Shin'ya Yamaguchi, Sekitoshi Kanai, Kazuki Adachi, Daiki Chijiwa
2024	C	`conf`	Analyzing Diffusion Models on Synthesizing Training Datasets. ACML Shin'ya Yamaguchi
2024	J	`jnl`	Evaluating Time-Series Training Dataset through Lens of Spectrum in Deep State Space Models. CoRR Sekitoshi Kanai, Yasutoshi Ida, Kazuki Adachi, Mihiro Uchida, Tsukasa Yoshida, Shin'ya Yamaguchi
2024	J	`jnl`	Explanation Bottleneck Models. CoRR Shin'ya Yamaguchi, Kosuke Nishida
2024	J	`jnl`	Key Factors Determining the Required Number of Training Images in Person Re-Identification. IEEE Access Taku Sasaki, Adam S. Walmsley, Kazuki Adachi, Shohei Enomoto, Shin'ya Yamaguchi
2024	B	`conf`	Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switching. IJCNN Shohei Enomoto, Naoya Hasegawa, Kazuki Adachi, Taku Sasaki, Shin'ya Yamaguchi, Satoshi Suzuki, Takeharu Eda
2024	J	`jnl`	Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switching. CoRR Shohei Enomoto, Naoya Hasegawa, Kazuki Adachi, Taku Sasaki, Shin'ya Yamaguchi, Satoshi Suzuki, Takeharu Eda
2024	J	`jnl`	Test-time Adaptation for Regression by Subspace Alignment. CoRR Kazuki Adachi, Shin'ya Yamaguchi, Atsutoshi Kumagai, Tomoki Hamagami
2024	B	`conf`	Test-time Similarity Modification for Person Re-identification toward Temporal Distribution Shift. IJCNN Kazuki Adachi, Shohei Enomoto, Taku Sasaki, Shin'ya Yamaguchi
2024	J	`jnl`	Test-time Similarity Modification for Person Re-identification toward Temporal Distribution Shift. CoRR Kazuki Adachi, Shohei Enomoto, Taku Sasaki, Shin'ya Yamaguchi
2024	C	`conf`	Toward Data Efficient Model Merging between Different Datasets without Performance Degradation. ACML Masanori Yamada, Tomoya Yamashita, Shin'ya Yamaguchi, Daiki Chijiwa
2023	A*	`conf`	Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff. ICCV Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Sekitoshi Kanai, Naoki Makishima, Atsushi Ando, Ryo Masumura
2023	J	`jnl`	Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff. CoRR Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Sekitoshi Kanai, Naoki Makishima, Atsushi Ando, Ryo Masumura
2023	B	`conf`	Covariance-Aware Feature Alignment with Pre-Computed Source Statistics for Test-Time Adaptation to Multiple Image Corruptions. ICIP Kazuki Adachi, Shin'ya Yamaguchi, Atsutoshi Kumagai
2023	C	`conf`	Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples. ACML Shin'ya Yamaguchi
2023	J	`jnl`	Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples. CoRR Shin'ya Yamaguchi
2023	J	`jnl`	On the Limitation of Diffusion Models for Synthesizing Training Datasets. CoRR Shin'ya Yamaguchi, Takuma Fukuda
2023	A*	`conf`	One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training. ICML Sekitoshi Kanai, Shin'ya Yamaguchi, Masanori Yamada, Hiroshi Takahashi, Kentaro Ohno, Yasutoshi Ida
2023	A*	`conf`	Regularizing Neural Networks with Meta-Learning Generative Models. NeurIPS Shin'ya Yamaguchi, Daiki Chijiwa, Sekitoshi Kanai, Atsutoshi Kumagai, Hisashi Kashima
2023	J	`jnl`	Regularizing Neural Networks with Meta-Learning Generative Models. CoRR Shin'ya Yamaguchi, Daiki Chijiwa, Sekitoshi Kanai, Atsutoshi Kumagai, Hisashi Kashima
2023	J	`jnl`	Revisiting Permutation Symmetry for Merging Models between Different Datasets. CoRR Masanori Yamada, Tomoya Yamashita, Shin'ya Yamaguchi, Daiki Chijiwa
2022	J	`jnl`	Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation. CoRR Kazuki Adachi, Shin'ya Yamaguchi, Atsutoshi Kumagai
2022	A	`conf`	Learning Robust Convolutional Neural Networks with Relevant Feature Focusing Via Explanations. ICME Kazuki Adachi, Shin'ya Yamaguchi
2022	J	`jnl`	Learning Robust Convolutional Neural Networks with Relevant Feature Focusing via Explanations. CoRR Kazuki Adachi, Shin'ya Yamaguchi
2022	A*	`conf`	Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks. NeurIPS Daiki Chijiwa, Shin'ya Yamaguchi, Atsutoshi Kumagai, Yasutoshi Ida
2022	J	`jnl`	Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks. CoRR Daiki Chijiwa, Shin'ya Yamaguchi, Atsutoshi Kumagai, Yasutoshi Ida
2022	J	`jnl`	Switching One-Versus-the-Rest Loss to Increase the Margin of Logits for Adversarial Robustness. CoRR Sekitoshi Kanai, Shin'ya Yamaguchi, Masanori Yamada, Hiroshi Takahashi, Yasutoshi Ida
2022	J	`jnl`	Transfer Learning with Pre-trained Conditional Generative Models. CoRR Shin'ya Yamaguchi, Sekitoshi Kanai, Atsutoshi Kumagai, Daiki Chijiwa, Hisashi Kashima
2021	B	`conf`	Constraining Logits by Bounded Function for Adversarial Robustness. IJCNN Sekitoshi Kanai, Masanori Yamada, Shin'ya Yamaguchi, Hiroshi Takahashi, Yasutoshi Ida
2021	A*	`conf`	F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain. ICCV Shin'ya Yamaguchi, Sekitoshi Kanai
2021	J	`jnl`	F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain. CoRR Shin'ya Yamaguchi, Sekitoshi Kanai
2021	B	`conf`	Image Enhanced Rotation Prediction for Self-Supervised Learning. ICIP Shin'ya Yamaguchi, Sekitoshi Kanai, Tetsuya Shioda, Shoichiro Takeda
2021	A*	`conf`	Pruning Randomly Initialized Neural Networks with Iterative Randomization. NeurIPS Daiki Chijiwa, Shin'ya Yamaguchi, Yasutoshi Ida, Kenji Umakoshi, Tomohiro Inoue
2021	J	`jnl`	Pruning Randomly Initialized Neural Networks with Iterative Randomization. CoRR Daiki Chijiwa, Shin'ya Yamaguchi, Yasutoshi Ida, Kenji Umakoshi, Tomohiro Inoue
2020	J	`jnl`	Constraining Logits by Bounded Function for Adversarial Robustness. CoRR Sekitoshi Kanai, Masanori Yamada, Shin'ya Yamaguchi, Hiroshi Takahashi, Yasutoshi Ida
2020	A*	`conf`	Effective Data Augmentation with Multi-Domain Learning GANs. AAAI Shin'ya Yamaguchi, Sekitoshi Kanai, Takeharu Eda
2019	J	`jnl`	Effective Data Augmentation with Multi-Domain Learning GANs. CoRR Shin'ya Yamaguchi, Sekitoshi Kanai, Takeharu Eda
2019	J	`jnl`	Multiple Pretext-Task for Self-Supervised Learning via Mixing Multiple Image Transformations. CoRR Shin'ya Yamaguchi, Sekitoshi Kanai, Tetsuya Shioda, Shoichiro Takeda
2017	—	`conf`	A Fusion Technique of Schema and Syntax Rules for Validating Open Data. ACIIDS (Extended Posters) Shin'ya Yamaguchi, Kimio Kuramitsu