Backbone architectures of most binary networks are well-known floating point (FP) architectures such as the ResNet family. Questioning that the architectures designed for FP networks might not be the best for binary networks, we propose to search architectures for binary networks (BNAS) by defining a new search space for binary architectures and a novel search objective. Specifically, based on the cell based search method, we define the new search space of binary layer types, design a new cell template, and rediscover the utility of and propose to use the Zeroise layer instead of using it as a placeholder. The novel search objective diversifies early search to learn better performing binary architectures. We show that our method searches architectures with stable training curves despite the quantization error inherent in binary networks. Quantitative analyses demonstrate that our searched architectures outperform the architectures used in state-of-the-art binary networks and outperform or perform on par with state-of-the-art binary networks that employ various techniques other than architectural changes. In addition, we further propose improvements to the training scheme of our searched architectures. With the new training scheme for our searched architectures, we achieve the state-of-the-art performance by binary networks by outperforming all previous methods by non-trivial margins.
翻译:多数二进制网络的后骨结构是众所周知的浮点( FP) 结构, 如 ResNet 家族 。 质疑为 FP 网络设计的结构可能不是二进制网络的最佳工具, 我们提议通过定义二进制结构的新搜索空间和一个新的搜索目标, 为二进制网络搜索结构( BNAS ) 。 具体地说, 我们根据基于单元格的搜索方法, 定义二进制层类型的新搜索空间, 设计一个新的单元格模板, 重新发现并提议使用Zeroise 层的效用, 而不是使用它作为占位符。 新的搜索目标将早期搜索化, 学习更好的运行二进制结构 。 我们显示, 尽管二进制结构中固有的四进制错误, 我们的方法搜索结构是稳定的。 定量分析表明, 我们的搜索结构超越了在最新二进制二进制网络中使用的架构, 超越了与新进制二进制网络的功能, 并且我们进一步建议通过新进制结构的搜索空间, 我们通过前进制的系统, 改进了前进制结构。