27 citations · 36 across the 8 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.CV2021
Multi-Dimensional Model Compression of Vision Transformer
Zejiang Hou, Sun-Yuan Kung
Vision transformers (ViT) have recently attracted considerable attentions, but the huge computational cost remains an issue for practical deployment. Previous ViT pruning methods t…
cs.CV2021
Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis
Zejiang Hou, Sun-Yuan Kung
We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category. Most of previous FSL approaches r…
cs.CV2021★ 5 cited
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
Xiaolong Ma, Minghai Qin, Fei Sun +7
Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation res…