Locality-Aware Adaptive Threshold Scaling for Efficient Binary Neural Networks Inference

This study proposes a novel technique to improve the efficiency of the inference based on binary neural networks (BNNs). In the proposed technique, the threshold, used to binarize feature elements, is adaptively scaled by considering the spatial localities inherent in feature maps, to skip redundant operations without degrading inference accuracy. A BNN inference processor supporting the proposed technique is designed and implemented, and the effectiveness of the proposed technique is evaluated with the implementation results of the processor. The proposed technique reduces the overall latency by 17.0%, while the inference accuracy is degraded by less than 1.56% for the CIFAR10 classification task. The resource efficiency is enhanced by up to 36.7%.