Top-1 ImageNet optimization promotes enormous networks that may be impractical in inference settings. Binary neural networks (BNNs) have the potential to significantly lower the compute intensity but existing models suffer from low quality. To overcome this deficiency, we propose PokeConv, a binary convolution block which improves quality of BNNs by techniques such as adding multiple residual paths, and tuning the activation function. We apply it to ResNet-50 and optimize ResNet's initial convolutional layer which is hard to binarize. We name the resulting network family PokeBNN. These techniques are chosen to yield favorable improvements in both top-1 accuracy and the network's cost. In order to enable joint optimization of the cost together with accuracy, we define arithmetic computation effort (ACE), a hardware- and energy-inspired cost metric for quantized and binarized networks. We also identify a need to optimize an under-explored hyper-parameter controlling the binarization gradient approximation. We establish a new, strong state-of-the-art (SOTA) on top-1 accuracy together with commonly-used CPU64 cost, ACE cost and network size metrics. ReActNet-Adam, the previous SOTA in BNNs, achieved a 70.5% top-1 accuracy with 7.9 ACE. A small variant of PokeBNN achieves 70.5% top-1 with 2.6 ACE, more than 3x reduction in cost; a larger PokeBNN achieves 75.6% top-1 with 7.8 ACE, more than 5% improvement in accuracy without increasing the cost. PokeBNN implementation in JAX/Flax and reproduction instructions are open sourced.

本文提出了 PokeConv，一个对二值神经网络(BNNs)卷积进行膨胀的方案，并对 ResNet-50 进行优化，进一步提高了准确性和网络的成本。通过定义算数计算代价(ACE)这样一个硬件和能源的成本度量标准，实现了准确性和成本的联合优化。此外，我们还发现了优化二进制跃迁的梯度近似的超参数的必要性。最终我们在 CPU64 成本、ACE 成本和网络大小这些公共度量标准下都取得了新的最佳成果，而且我们提出的 PokeBNN 型网络成本低、准确率高。

PokeBNN：轻量级准确性的二进制追求