An Efficient Quantitative Approach for Optimizing Convolutional Neural Networks

no code implementations • 11 Sep 2020 • Yuke Wang, Boyuan Feng, Xueqiao Peng, Yufei Ding

To clear these hurdles, we propose 3D-Receptive Field (3DRF), an explainable and easy-to-compute metric, to estimate the quality of a CNN architecture and guide the search process of designs.

Image Classification object-detection +1

SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization

no code implementations • 9 Jul 2020 • Boyuan Feng, yuke wang, Xu Li, Shu Yang, Xueqiao Peng, Yufei Ding

With the increasing popularity of graph-based learning, Graph Neural Networks (GNNs) win lots of attention from the research and industry field because of their high accuracy.

Quantization