Boosting explainability of general visual inspection with a multihead vision-language model.

Hiroaki Aizawa

Shiryu Ueno Yoshikazu Hayashi Shunsuke Nakatsuka Hiroaki Aizawa Kunihito Kato Boosting explainability of general visual inspection with a multihead vision-language model. 2026 35 J. Electronic Imaging 3 https://doi.org/10.1117/1.jei.35.3.031204 db/journals/jei/jei35.html#UenoHNAK26 streams/journals/jei

Hiroaki Aizawa Yuki Igaue Rényi Attention Entropy for Patch Pruning. 2026 April abs/2604.03803 CoRR https://doi.org/10.48550/arXiv.2604.03803 db/journals/corr/corr2604.html#abs-2604-03803 streams/journals/corr

Yuki Igaue Hiroaki Aizawa Patch Pruning Strategy Based on Robust Statistical Measures of Attention Weight Diversity in Vision Transformers. 123-133 2025 ACPR (2) https://doi.org/10.1007/978-981-95-4398-4_9 conf/acpr/2025-2 db/conf/acpr/acpr2025-2.html#IgaueA25 streams/conf/acpr Hiroaki Aizawa Yuta Naito Kohei Fukuda Class-Wise Flooding Regularization for Imbalanced Image Classification. 177-187 2025 ACPR (2) https://doi.org/10.1007/978-981-95-4398-4_13 conf/acpr/2025-2 db/conf/acpr/acpr2025-2.html#AizawaNF25 streams/conf/acpr Akito Shinohara Kohei Fukuda Hiroaki Aizawa Logit Mixture Outlier Exposure for Fine-Grained Out-Of-Distribution Detection. 1-7 2025 DICTA https://doi.org/10.1109/DICTA68720.2025.11302494 conf/dicta/2025 db/conf/dicta/dicta2025.html#ShinoharaFA25 Sota Ito Yoshikazu Hayashi Hiroaki Aizawa Kunihito Kato Learning Neural Velocity Fields from Dynamic 3D Scenes via Inter-Frame Consistency Loss. 1-8 2025 IJCNN https://doi.org/10.1109/IJCNN64981.2025.11228866 conf/ijcnn/2025 db/conf/ijcnn/ijcnn2025.html#ItoHAK25 streams/conf/ijcnn Kohei Fukuda Hiroaki Aizawa Adaptive Out-of-Distribution Detection with Coarse-to-Fine Grained Representation. 19-26 2025 VISIGRAPP (2): VISAPP https://doi.org/10.5220/0013100100003912 conf/visigrapp/2025-2 db/conf/visigrapp/visigrapp2025-2.html#FukudaA25 Shiryu Ueno Yoshikazu Hayashi Shunsuke Nakatsuka Yusei Yamada Hiroaki Aizawa Kunihito Kato Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model. 253-260 2025 VISIGRAPP (2): VISAPP https://doi.org/10.5220/0013088100003912 conf/visigrapp/2025-2 db/conf/visigrapp/visigrapp2025-2.html#UenoHNYAK25 Sota Ito Yoshikazu Hayashi Hiroaki Aizawa Kunihito Kato Learning Neural Velocity Fields from Dynamic 3D Scenes via Edge-Aware Ray Sampling. 699-706 2025 VISIGRAPP (2): VISAPP https://doi.org/10.5220/0013233600003912 conf/visigrapp/2025-2 db/conf/visigrapp/visigrapp2025-2.html#ItoHAK25

Shiryu Ueno Yoshikazu Hayashi Shunsuke Nakatsuka Yusei Yamada Hiroaki Aizawa Kunihito Kato Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model. 2025 February abs/2502.09057 CoRR https://doi.org/10.48550/arXiv.2502.09057 db/journals/corr/corr2502.html#abs-2502-09057 streams/journals/corr

Yuki Igaue Hiroaki Aizawa Patch Pruning Strategy Based on Robust Statistical Measures of Attention Weight Diversity in Vision Transformers. 2025 July abs/2507.19175 CoRR https://doi.org/10.48550/arXiv.2507.19175 db/journals/corr/corr2507.html#abs-2507-19175 streams/journals/corr

Hiroaki Aizawa Yuta Naito Kohei Fukuda Class-wise Flooding Regularization for Imbalanced Image Classification. 2025 August abs/2508.18723 CoRR https://doi.org/10.48550/arXiv.2508.18723 db/journals/corr/corr2508.html#abs-2508-18723 streams/journals/corr

Hiroaki Aizawa Yoshikazu Hayashi Flatness-aware Curriculum Learning via Adversarial Difficulty. 2025 August abs/2508.18726 CoRR https://doi.org/10.48550/arXiv.2508.18726 db/journals/corr/corr2508.html#abs-2508-18726 streams/journals/corr

Akito Shinohara Kohei Fukuda Hiroaki Aizawa Logit Mixture Outlier Exposure for Fine-grained Out-of-Distribution Detection. 2025 September abs/2509.11892 CoRR https://doi.org/10.48550/arXiv.2509.11892 db/journals/corr/corr2509.html#abs-2509-11892 streams/journals/corr

Takeshi Yoshidomi Shinji Kume Hiroaki Aizawa Akira Furui Classification of Carotid Plaque with Jellyfish Sign Through Convolutional and Recurrent Neural Networks Utilizing Plaque Surface Edges. 1-4 2024 EMBC https://doi.org/10.1109/EMBC53108.2024.10782813 conf/embc/2024 db/conf/embc/embc2024.html#YoshidomiKAF24 Yuki Igaue Takio Kurita Hiroaki Aizawa Incorporating Spatial Locality Into Self-attention for Training Vision Transformer on Small-Scale Datasets. 259-274 2024 ICPR (3) https://doi.org/10.1007/978-3-031-78122-3_17 conf/icpr/2024-3 db/conf/icpr/icpr2024-3.html#IgaueKA24 streams/conf/icpr Kohei Fukuda Takio Kurita Hiroaki Aizawa Important Pixels Sampling for NeRF Training Based on Edge Values and Squared Errors Between the Ground Truth and the Estimated Colors. 102-111 2024 VISIGRAPP (2): VISAPP https://doi.org/10.5220/0012346200003660 conf/visigrapp/2024-2 db/conf/visigrapp/visigrapp2024-2.html#FukudaKA24

Takeshi Yoshidomi Shinji Kume Hiroaki Aizawa Akira Furui Classification of Carotid Plaque with Jellyfish Sign Through Convolutional and Recurrent Neural Networks Utilizing Plaque Surface Edges. 2024 abs/2406.18919 CoRR https://doi.org/10.48550/arXiv.2406.18919 db/journals/corr/corr2406.html#abs-2406-18919 streams/journals/corr

Kohei Fukuda Hiroaki Aizawa Taylor Outlier Exposure. 2024 abs/2412.07219 CoRR https://doi.org/10.48550/arXiv.2412.07219 db/journals/corr/corr2412.html#abs-2412-07219 streams/journals/corr

Hiroaki Aizawa Itoshi Naramura Eigengrasp-Conditioned Neural Radiance Fields. 121629-121636 2023 11 IEEE Access https://doi.org/10.1109/ACCESS.2023.3328625 db/journals/access/access11.html#AizawaN23

Yin Wang Hiroaki Aizawa Takio Kurita Image Inpainting for Large and Irregular Mask Based on Partial Convolution and Cross Semantic Attention. 115-128 2023 ACPR (2) https://doi.org/10.1007/978-3-031-47637-2_9 conf/acpr/2023-2 db/conf/acpr/acpr2023-2.html#WangAK23 Sota Ito Hiroaki Aizawa Kunihito Kato Few-Shot NeRF-Based View Synthesis for Viewpoint-Biased Camera Pose Estimation. 308-319 2023 ICANN (2) https://doi.org/10.1007/978-3-031-44210-0_25 conf/icann/2023-2 db/conf/icann/icann2023-2.html#ItoAK23 streams/conf/icann Kohei Fukuda Takio Kurita Hiroaki Aizawa Neural Radiance Fields with Regularizer Based on Differences of Neighboring Pixels. 1-7 2023 IJCNN https://doi.org/10.1109/IJCNN54540.2023.10191946 conf/ijcnn/2023 db/conf/ijcnn/ijcnn2023.html#FukudaKA23 Jiazhou Zheng Hiroaki Aizawa Takio Kurita Facial Image Manipulation via Discriminative Decomposition of Semantic Space. 1-8 2023 IJCNN https://doi.org/10.1109/IJCNN54540.2023.10191767 conf/ijcnn/2023 db/conf/ijcnn/ijcnn2023.html#ZhengAK23 Itsuki Ueda Yoshihiro Fukuhara Hirokatsu Kataoka Hiroaki Aizawa Hidehiko Shishido Itaru Kitahara Neural Density-Distance Fields. 53-68 2022 ECCV (32) https://doi.org/10.1007/978-3-031-19824-3_4 conf/eccv/2022-32 db/conf/eccv/eccv2022-32.html#UedaFKASK22 Jiazhou Zheng Hiroaki Aizawa Takio Kurita Additional Learning for Joint Probability Distribution Matching in BiGAN. 165-176 2022 ICONIP (1) https://doi.org/10.1007/978-3-031-30105-6_14 conf/iconip/2022-1 db/conf/iconip/iconip2022-1.html#ZhengAK22

Itsuki Ueda Yoshihiro Fukuhara Hirokatsu Kataoka Hiroaki Aizawa Hidehiko Shishido Itaru Kitahara Neural Density-Distance Fields. 2022 abs/2207.14455 CoRR https://doi.org/10.48550/arXiv.2207.14455 db/journals/corr/corr2207.html#abs-2207-14455

Yukihiro Domae Hiroaki Aizawa Kunihito Kato Multi-scale Global Reasoning Unit for Semantic Segmentation. 46-56 2021 IW-FCV https://doi.org/10.1007/978-3-030-81638-4_4 conf/fcv/2021 db/conf/fcv/fcv2021.html#DomaeAK21 Hiroaki Aizawa Hirokatsu Kataoka Yutaka Satoh Kunihito Kato Viewpoint-agnostic Image Rendering. 3802-3811 2021 WACV https://doi.org/10.1109/WACV48630.2021.00385 conf/wacv/2021 db/conf/wacv/wacv2021.html#AizawaKSK21

Hiroaki Aizawa Yukihiro Domae Kunihito Kato Hierarchical Pyramid Representations for Semantic Segmentation. 2021 abs/2104.01792 CoRR https://arxiv.org/abs/2104.01792 db/journals/corr/corr2104.html#abs-2104-01792

Keisuke Goto 0005 Kunihito Kato Takaho Saito Hiroaki Aizawa Adversarial autoencoder for detecting anomalies in soldered joints on printed circuit boards. 041013 2020 29 J. Electronic Imaging 4 https://doi.org/10.1117/1.JEI.29.4.041013 db/journals/jei/jei29.html#GotoKSA20

Kyosuke Komoto Hiroaki Aizawa Kunihito Kato Consistency Ensured Bi-directional GAN for Anomaly Detection. 236-247 2020 IW-FCV https://doi.org/10.1007/978-981-15-4818-5_18 conf/fcv/2020 db/conf/fcv/fcv2020.html#KomotoAK20 Hiroaki Aizawa Hirokatsu Kataoka Yutaka Satoh Kunihito Kato Disentangle, Assemble, and Synthesize: Unsupervised Learning to Disentangle Appearance and Location. 2065-2072 2020 ICPR https://doi.org/10.1109/ICPR48806.2021.9413032 conf/icpr/2020 db/conf/icpr/icpr2020.html#AizawaKSK20 Takeshi Hara Naoto Matoba Xiangrong Zhou Shinya Yokoi Hiroaki Aizawa Hiroshi Fujita 0001 Keiji Sakashita Tetsuya Matsuoka Automated detection of extradural and subdural hematoma for contrast-enhanced CT images in emergency medical care. 651432 2007 Computer-Aided Diagnosis https://doi.org/10.1117/12.710307 conf/micad/2007 db/conf/micad/micad2007.html#HaraMZYA0SM07

Eiji Toba Masahiro Ichikawa Junji Kazama Toyonori Nishimatsu Hiroaki Aizawa Development of Oxygen Sensor Using Fiber-optics Coupler. 278-282 1998 10 J. Robotics Mechatronics 3 https://doi.org/10.20965/jrm.1998.p0278 db/journals/jrm/jrm10.html#TobaIKNA98

Yukihiro Domae Hiroshi Fujita 0001 Kohei Fukuda Yoshihiro Fukuhara Akira Furui Keisuke Goto 0005 Takeshi Hara Yoshikazu Hayashi Masahiro Ichikawa Yuki Igaue Sota Ito Hirokatsu Kataoka Kunihito Kato Junji Kazama Itaru Kitahara Kyosuke Komoto Shinji Kume Takio Kurita Naoto Matoba Tetsuya Matsuoka Yuta Naito Shunsuke Nakatsuka Itoshi Naramura Toyonori Nishimatsu Takaho Saito Keiji Sakashita Yutaka Satoh Akito Shinohara Hidehiko Shishido Eiji Toba Itsuki Ueda Shiryu Ueno Yin Wang Yusei Yamada Shinya Yokoi Takeshi Yoshidomi Jiazhou Zheng Xiangrong Zhou