ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions
european conference on computer vision, pp. 143-159, 2020.
In this paper, we propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost. We first construct a baseline network by modifying and binarizing a compact real-valued network with parameter-free shortcuts, bypassing all the intermediate convol...More
PPT (Upload PPT)