222 citations · 236 across the 4 of their papers we have counts for
4 papers
Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again
Xin-Chun Li, Wen-Shu Fan, Shaoming Song +4
Knowledge Distillation (KD) aims at transferring the knowledge of a well-performed neural network (the {\it teacher}) to a weaker one (the {\it student}). A peculiar phenomenon is…
Efficient textual explanations for complex road and traffic scenarios based on semantic segmentation
Yiyue Zhao, Xinyu Yun, Chen Chai +3
The complex driving environment brings great challenges to the visual perception of autonomous vehicles. It's essential to extract clear and explainable information from the comple…
DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science
Mufei Li, Jinjing Zhou, Jiajing Hu +4
Graph neural networks (GNNs) constitute a class of deep learning methods for graph data. They have wide applications in chemistry and biology, such as molecular property prediction…
A New Training Framework for Deep Neural Network
Zhenyan Hou, Wenxuan Fan
Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the l…