1 citations · 1 across the 3 of their papers we have counts for
4 papers
Sparsity-Adaptive Sharpness-Aware Minimization
Shiryu Ueno, Yoshikazu Hayashi, Kunihito Kato
Deploying deep neural networks in real-world settings requires models that are both compact and robust to common corruptions. However, at deployment-relevant high sparsity, standar…
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…
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…
Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model
Shiryu Ueno, Yoshikazu Hayashi, Shunsuke Nakatsuka +3
We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as…