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.

本文综述了二值神经网络中直接二值化和优化二值化两种算法，其中优化二值化采用了诸如最小化量化误差、改进神经网络损失函数、减少梯度误差等技术来解决二值化不可避免的严重信息损失和优化难题；同时对硬件友好设计和训练技巧等实用方面也进行了讨论，最后对图像分类、目标检测和语义分割等不同任务进行了评估和讨论，并展望了未来研究中可能面临的挑战。

二元神经网络：综述