Searching for Accurate Binary Neural Architectures
This work addresses the efficiency-accuracy trade-off for deploying neural networks on mobile devices, representing an incremental improvement in binary network design.
The authors tackled the problem of low accuracy in binary neural networks by developing an automated framework to search for compact and accurate binary architectures, achieving performance comparable to full-precision models with acceptable increases in model size and calculations.
Binary neural networks have attracted tremendous attention due to the efficiency for deploying them on mobile devices. Since the weak expression ability of binary weights and features, their accuracy is usually much lower than that of full-precision (i.e. 32-bit) models. Here we present a new frame work for automatically searching for compact but accurate binary neural networks. In practice, number of channels in each layer will be encoded into the search space and optimized using the evolutionary algorithm. Experiments conducted on benchmark datasets and neural architectures demonstrate that our searched binary networks can achieve the performance of full-precision models with acceptable increments on model sizes and calculations.