Duong H. Le
Duong H. Le
Home
Publications
Light
Dark
Automatic
1
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples
We leverage samples from distractor classes or randomly generated noise to improve the generalization of few-shot learner
Duong H. Le*
,
Khoi D. Nguyen*
,
Khoi Nguyen
,
Quoc-Huy Tran
,
Rang Nguyen
,
Binh-Son Hua
PDF
Cite
Code
Network Pruning that Matters: A Case Study on Retraining Variants
We study the effective of different retraining mechanisms while doing pruning.
Duong H. Le
,
Binh-Son Hua
PDF
Cite
Code
Slides
Video
Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation
We propose KESI - a method that combine knowledge distillation, network pruning and ensemble learning to improve the performance of compact networks.
Duong H. Le
,
Trung-Nhan Vo
,
Nam Thoai
PDF
Cite
Code
Poster
Video
Cite
×