Moseli Mots’Oehli

Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise

2025 · arXiv (Cornell University)

Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformers in similar scenarios, particularly under label noise, remains largely unexplored. Given …