5 papers
Temperature-Adaptive Transformed Teacher Matching
Hiroaki Aizawa, Yoshikazu Hayashi
Temperature scaling is a core component of knowledge distillation, yet its role and effect are still not fully understood. Transformed Teacher Matching (TTM) clarifies the role of…
Polynomial Dice Loss for Medical Image Segmentation
Hiroaki Aizawa
Medical image segmentation is a fundamental task for medical image processing and computer-assisted intervention, yet data imbalance and small lesion detection pose significant cha…
Flatness-aware Curriculum Learning via Adversarial Difficulty
Hiroaki Aizawa, Yoshikazu Hayashi
Neural networks trained by empirical risk minimization often suffer from overfitting, especially to specific samples or domains, which leads to poor generalization. Curriculum Lear…
Patch Pruning Strategy Based on Robust Statistical Measures of Attention Weight Diversity in Vision Transformers
Yuki Igaue, Hiroaki Aizawa
Multi-head self-attention is a distinctive feature extraction mechanism of vision transformers that computes pairwise relationships among all input patches, contributing significan…
Classification of Carotid Plaque with Jellyfish Sign Through Convolutional and Recurrent Neural Networks Utilizing Plaque Surface Edges
Takeshi Yoshidomi, Shinji Kume, Hiroaki Aizawa +1
In carotid arteries, plaque can develop as localized elevated lesions. The Jellyfish sign, marked by fluctuating plaque surfaces with blood flow pulsation, is a dynamic characteris…