3 papers
cs.LG2025
FoCTTA: Low-Memory Continual Test-Time Adaptation with Focus
Youbing Hu, Yun Cheng, Zimu Zhou +3
Continual adaptation to domain shifts at test time (CTTA) is crucial for enhancing the intelligence of deep learning enabled IoT applications. However, prevailing TTA methods, whic…
cs.CV2025
SAC-ViT: Semantic-Aware Clustering Vision Transformer with Early Exit
Youbing Hu, Yun Cheng, Anqi Lu +2
The Vision Transformer (ViT) excels in global modeling but faces deployment challenges on resource-constrained devices due to the quadratic computational complexity of its attentio…
cs.CV2025
FocusDD: Real-World Scene Infusion for Robust Dataset Distillation
Youbing Hu, Yun Cheng, Olga Saukh +4
Dataset distillation has emerged as a strategy to compress real-world datasets for efficient training. However, it struggles with large-scale and high-resolution datasets, limiting…