Abstract The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error. We also investigate other practical aspects of binary neural networks such as the hardware-friendly design and the training tricks. Then, we give the evaluation and discussions on different tasks, including image classification, object detection and semantic segmentation. Finally, the challenges that may be faced in future research are prospected.

中文翻译：

---

二元神经网络：调查

摘要 二元神经网络在很大程度上节省了存储和计算，是在资源有限的设备上部署深度模型的一种很有前途的技术。然而，二值化不可避免地会造成严重的信息丢失，更糟糕的是，它的不连续性给深度网络的优化带来了困难。为了解决这些问题，近年来提出了多种算法，并取得了令人满意的进展。在本文中，我们对这些算法进行了全面的调查，主要分为直接进行二值化的原生解决方案，以及使用最小化量化误差、改进网络损失函数和减少梯度误差等技术的优化解决方案。我们还研究了二元神经网络的其他实际方面，例如硬件友好的设计和训练技巧。然后，我们对不同的任务进行了评估和讨论，包括图像分类、目标检测和语义分割。最后，对未来研究中可能面临的挑战进行了展望。