28 citations · 41 across the 6 of their papers we have counts for
6 papers
CORSD: Class-Oriented Relational Self Distillation
Muzhou Yu, Sia Huat Tan, Kailu Wu +3
Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature…
Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention
Sia Huat Tan, Runpei Dong, Kaisheng Ma
Most feedforward convolutional neural networks spend roughly the same efforts for each pixel. Yet human visual recognition is an interaction between eye movements and spatial atten…
PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators
Zhanhong Tan, Jiebo Song, Xiaolong Ma +8
Weight pruning is a powerful technique to realize model compression. We propose PCNN, a fine-grained regular 1D pruning method. A novel index format called Sparsity Pattern Mask (S…
Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation
Shaokai Ye, Kailu Wu, Mu Zhou +6
Existing domain adaptation methods aim at learning features that can be generalized among domains. These methods commonly require to update source classifier to adapt to the target…
Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?
Xiaolong Ma, Sheng Lin, Shaokai Ye +10
Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or S…
Brain-inspired reverse adversarial examples
Shaokai Ye, Sia Huat Tan, Kaidi Xu +3
A human does not have to see all elephants to recognize an animal as an elephant. On contrast, current state-of-the-art deep learning approaches heavily depend on the variety of tr…