加宽和压缩：实现精确和高效的QNN
Widening and Squeezing: Towards Accurate and Efficient QNNs
摘要：
量化神经网络（QNN）以其极低的计算和存储开销而备受业界青睐，但其性能仍不如全精度参数网络。大多数现有的方法旨在通过利用更有效的训练技术来提高QNN特别是二进制神经网络的性能。然而，我们发现量化特征的表示能力远远弱于全精度特征。我们通过将原始全精度网络中的特征投影到高维量化特征来解决这个问题。同时，冗余的量化特征将被消除，以避免某些数据集的维度不受限制地增长。然后，一个紧凑的量化神经网络，但具有足够的表示能力将被建立。在基准数据集上的实验结果表明，该方法能够以更少的参数和计算量建立QNN，但与全精度基线模型的性能几乎相同，例如ImageNet ILSVRC 2012数据集上二进制ResNet-18的$29.9\%$ top-1错误。
英文摘要：
Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. However, we find the representation capability of quantization features is far weaker than full-precision features by experiments. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features. Simultaneously, redundant quantization features will be eliminated in order to avoid unrestricted growth of dimensions for some datasets. Then, a compact quantization neural network but with sufficient representation ability will be established. Experimental results on benchmark datasets demonstrate that the proposed method is able to establish QNNs with much less parameters and calculations but almost the same performance as that of full-precision baseline models, e.g. $29.9\%$ top-1 error of binary ResNet-18 on the ImageNet ILSVRC 2012 dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
