research
∙
04/28/2023
CORSD: Class-Oriented Relational Self Distillation
Knowledge distillation conducts an effective model compression method wh...
share
research
∙
11/03/2021
Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention
Most feedforward convolutional neural networks spend roughly the same ef...
research
∙
02/11/2020
PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators
Weight pruning is a powerful technique to realize model compression. We ...
research
∙
11/28/2019
Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation
Existing domain adaptation methods aim at learning features that can be ...
research
∙
07/03/2019
Non-structured DNN Weight Pruning Considered Harmful
Large deep neural network (DNN) models pose the key challenge to energy ...
research
∙
05/28/2019