Binary neural networks are the extreme case of network quantization, which has long been thought of as a potential edge machine learning solution. However, the significant accuracy gap to the full-precision counterparts restricts their creative potential for mobile applications. In this work, we revisit the potential of binary neural networks and focus on a compelling but unanswered problem: how can a binary neural network achieve the crucial accuracy level (e.g., 80%) on ILSVRC-2012 ImageNet? We achieve this goal by enhancing the optimization process from three complementary perspectives: (1) We design a novel binary architecture BNext based on a comprehensive study of binary architectures and their optimization process. (2) We propose a novel knowledge-distillation technique to alleviate the counter-intuitive overfitting problem observed when attempting to train extremely accurate binary models. (3) We analyze the data augmentation pipeline for binary networks and modernize it with up-to-date techniques from full-precision models. The evaluation results on ImageNet show that BNext, for the first time, pushes the binary model accuracy boundary to 80.57% and significantly outperforms all the existing binary networks. Code and trained models are available at: https://github.com/hpi-xnor/BNext.git.
翻译:网络二进制神经网络是网络量化的极端案例,长期以来一直被认为是潜在的边缘机器学习解决方案。 但是,完全精准对应方的精度差距巨大,限制了其移动应用的创造潜力。 在这项工作中,我们重新审视二进制神经网络的潜力,并侧重于一个令人生动但未解答的问题:二进制神经网络如何在 ILSVRC-2012图像网络上达到关键的精确度(例如,80%)?我们通过从三个互补角度加强优化进程来实现这一目标:(1) 我们根据对二进制建筑及其优化进程的全面研究,设计了一个新的二进制建筑BNext。 (2) 我们提出了一种新的知识蒸馏技术,以缓解在试图训练极准确的二进制模型时观察到的反直觉过度的问题。(3) 我们分析了二进制神经网络的数据增强管道,并用全精度精度模型的最新技术将其现代化。 图像网络的评估结果显示,第一次将二进制模型的精确度边界推至80.57%,并大大超越了现有的二进式网络。 MAGI/FIGNGR。