most citedEstimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2023★ 1 cited

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

Xiao-Ming Wu, Dian Zheng, Zuhao Liu +1

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradient…