Open access
Jul 2026
Uncertainty-Guided Adaptive Knowledge Distillation for Lightweight Cross-Domain Object Detection
This article introduces Uncertainty-Guided Adaptive Knowledge Distillation (UGAKD), a novel framework designed to enhance UDA while simultaneously reducing model size through targeted knowledge distillation and proposing a two-stage, difficulty-aware training scheme to facilitate learning.
Wei-Lun Tseng, Yi-Lun Wu, Yung-Hui Li et al.
· ACM Transactions on Intellig... · 0 citations