Semantic segmentation is a popular research topic in computer vision, and many efforts have been made on it with impressive results. In this paper, we intend to search an optimal network structure that can run in real-time for this problem. Towards this goal, we jointly search the depth, channel, dilation rate and feature spatial resolution, which results in a search space consisting of about 2.78*10^324 possible choices. To handle such a large search space, we leverage differential architecture search methods. However, the architecture parameters searched using existing differential methods need to be discretized, which causes the discretization gap between the architecture parameters found by the differential methods and their discretized version as the final solution for the architecture search. Hence, we relieve the problem of discretization gap from the innovative perspective of solution space regularization. Specifically, a novel Solution Space Regularization (SSR) loss is first proposed to effectively encourage the supernet to converge to its discrete one. Then, a new Hierarchical and Progressive Solution Space Shrinking method is presented to further achieve high efficiency of searching. In addition, we theoretically show that the optimization of SSR loss is equivalent to the L_0-norm regularization, which accounts for the improved search-evaluation gap. Comprehensive experiments show that the proposed search scheme can efficiently find an optimal network structure that yields an extremely fast speed (175 FPS) of segmentation with a small model size (1 M) while maintaining comparable accuracy.

翻译：语义分解是计算机视野中一个受欢迎的研究主题,对此已经做出了许多努力,并取得了令人印象深刻的结果。 在本文件中,我们打算寻找一个可以实时运行的优化网络结构,以解决这一问题。为此,我们共同搜索深度、通道、通缩率和空间分辨率特征,从而形成一个由大约2.78*10324可能选择组成的搜索空间。为了处理这样一个巨大的搜索空间,我们利用了差异结构搜索方法。然而,使用现有差异方法搜索的建筑参数需要分解,从而造成差异方法发现的结构参数与作为建筑搜索最终解决方案的离散版本之间的离散差距。因此,我们从空间正规化的创新角度来缓解离散差距问题。具体地说,新颖的空间整化(SSR)损失是为了有效地鼓励超级网络与其离散空间的连接。然后,提出了一种新的高度和渐进式空间整化方法,以进一步提高搜索效率。 此外,我们理论上显示,在结构上的差异最优化的SSR损失是类似于快速的搜索模式(I10-noral),同时提出一个快速的搜索模型显示,快速搜索模式可以显示,快速的升级的模型可以显示快速搜索模式。