3 papers
cs.CV2025
Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation
Shohei Enomoto
Visual prompting (VP) has emerged as a promising parameter-efficient fine-tuning approach for adapting pre-trained vision models to downstream tasks without modifying model paramet…
cs.LG2025
Pseudo Multi-Source Domain Generalization: Bridging the Gap Between Single and Multi-Source Domain Generalization
Shohei Enomoto
Deep learning models often struggle to maintain performance when deployed on data distributions different from their training data, particularly in real-world applications where en…
stat.ML2024
EntProp: High Entropy Propagation for Improving Accuracy and Robustness
Shohei Enomoto
Deep neural networks (DNNs) struggle to generalize to out-of-distribution domains that are different from those in training despite their impressive performance. In practical appli…