In this work, we present BasisNet which combines recent advancements in
efficient neural network architectures, conditional computation, and early
termination in a simple new form. Our approach incorporates a lightweight model
to preview the input and generate input-dependent combination coefficients,
which later controls the synthesis of a more accurate specialist model to make
final prediction. The two-stage model synthesis strategy can be applied to any
network architectures and both stages are jointly trained. We also show that
proper training recipes are critical for increasing generalizability for such
high capacity neural networks. On ImageNet classification benchmark, our
BasisNet with MobileNets as backbone demonstrated clear advantage on
accuracy-efficiency trade-off over several strong baselines. Specifically,
BasisNet-MobileNetV3 obtained 80.3% top-1 accuracy with only 290M Multiply-Add
operations, halving the computational cost of previous state-of-the-art without
sacrificing accuracy. With early termination, the average cost can be further
reduced to 198M MAdds while maintaining accuracy of 80.0% on ImageNet.

本文提出了 BasisNet，它采用轻量级模型和两阶段模型合成策略，结合了高效神经网络体系结构、条件计算和早期终止，具有高效且精确的性能。在 ImageNet 分类基准测试中，使用 BasisNet 的 MobileNets 作为骨干网络，相比于其他基准测试，BasisNet-MobileNetV3 获得了显著的精度 - 效率平衡优势，仅需 290M 的乘加操作即可达到 80.3% 的 top-1 准确率，而且在不降低准确率的情况下，平均成本可进一步降低至 198M MAdds。