62 citations · 78 across the 12 of their papers we have counts for
11 papers · 1 filter
Screening Is Effective for Visual Recognition
Shunya Shimomura, Kazuhiro Hotta
Vision Transformer (ViT) has been widely used as a powerful framework for modeling global dependencies among image patches. However, its core component, self-attention assigns soft…
Lite-HRNet Plus: Fast and Accurate Facial Landmark Detection
Sota Kato, Kazuhiro Hotta, Yuhki Hatakeyama +1
Facial landmark detection is an essential technology for driver status tracking and has been in demand for real-time estimations. As a landmark coordinate prediction, heatmap-based…
Enlarged Large Margin Loss for Imbalanced Classification
Sota Kato, Kazuhiro Hotta
We propose a novel loss function for imbalanced classification. LDAM loss, which minimizes a margin-based generalization bound, is widely utilized for class-imbalanced image classi…
DeformableFormer: Classification of Endoscopic Ultrasound Guided Fine Needle Biopsy in Pancreatic Diseases
Taiji Kurami, Takuya Ishikawa, Kazuhiro Hotta
Endoscopic Ultrasound-Fine Needle Aspiration (EUS-FNA) is used to examine pancreatic cancer. EUS-FNA is an examination using EUS to insert a thin needle into the tumor and collect…
One-shot and Partially-Supervised Cell Image Segmentation Using Small Visual Prompt
Sota Kato, Kazuhiro Hotta
Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training.…
Reconstructed Student-Teacher and Discriminative Networks for Anomaly Detection
Shinji Yamada, Satoshi Kamiya, Kazuhiro Hotta
Anomaly detection is an important problem in computer vision; however, the scarcity of anomalous samples makes this task difficult. Thus, recent anomaly detection methods have used…