2 citations · 2 across the 1 of their papers we have counts for
2 papers
cs.CV2019★ 2 cited
Distilling Pixel-Wise Feature Similarities for Semantic Segmentation
Yuhu Shan
Among the neural network compression techniques, knowledge distillation is an effective one which forces a simpler student network to mimic the output of a larger teacher network.…
cs.CV2018
Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving
Yuhu Shan, Wen Feng Lu, Chee Meng Chew
Annotating large scale datasets to train modern convolutional neural networks is prohibitively expensive and time-consuming for many real tasks. One alternative is to train the mod…