Binary neural networks utilize 1-bit quantized weights and activations to
reduce both the model's storage demands and computational burden. However,
advanced binary architectures still incorporate millions of inefficient and
nonhardware-friendly full-precision multiplication operations. A&B BNN is
proposed to directly remove part of the multiplication operations in a
traditional BNN and replace the rest with an equal number of bit operations,
introducing the mask layer and the quantized RPReLU structure based on the
normalizer-free network architecture. The mask layer can be removed during
inference by leveraging the intrinsic characteristics of BNN with
straightforward mathematical transformations to avoid the associated
multiplication operations. The quantized RPReLU structure enables more
efficient bit operations by constraining its slope to be integer powers of 2.
Experimental results achieved 92.30%, 69.35%, and 66.89% on the CIFAR-10,
CIFAR-100, and ImageNet datasets, respectively, which are competitive with the
state-of-the-art. Ablation studies have verified the efficacy of the quantized
RPReLU structure, leading to a 1.14% enhancement on the ImageNet compared to
using a fixed slope RLeakyReLU. The proposed add&bit-operation-only BNN offers
an innovative approach for hardware-friendly network architecture.

二进制神经网络使用 1 位量化的权重和激活来减少模型的存储需求和计算负担。本文提出了 A&B BNN，在传统的 BNN 中直接移除了一部分乘法运算并用相等数量的位运算代替其余部分，引入了掩码层和基于无正则化网络架构的量化 RPReLU 结构。掩码层可以通过数学变换避免相关的乘法运算。量化 RPReLU 结构通过限制其斜率为 2 的整数幂，实现更高效的位运算。实验结果在 CIFAR-10、CIFAR-100 和 ImageNet 数据集上分别达到 92.30%、69.35% 和 66.89%，与最先进方法相当。消融实验验证了量化 RPReLU 结构的有效性，与使用固定斜率 RLeakyReLU 相比，在 ImageNet 上提升了 1.14%。提出的仅添加位操作的 BNN 为硬件友好型网络架构提供了创新的方法。