Signed Binary Weight Networks: Improving Efficiency of Binary Weight Networks by Exploiting Sparsity

Efficient inference of Deep Neural Networks (DNNs) is essential to making AI ubiquitous. Two important algorithmic techniques have shown promise for enabling efficient inference - sparsity and binarization. These techniques translate into weight sparsity and weight repetition at the hardware-software level allowing the deployment of DNNs with critically low power and latency requirements. We propose a new method called signed-binary networks to improve further efficiency (by exploiting both weight sparsity and weight repetition) while maintaining similar accuracy. Our method achieves comparable accuracy on ImageNet and CIFAR10 datasets with binary and can lead to $>69\%$ sparsity. We observe real speedup when deploying these models on general-purpose devices. We show that this high percentage of unstructured sparsity can lead to a further ~2x reduction in energy consumption on ASICs with respect to binary.