We propose a fully differentiable architecture for simultaneous semantic and instance segmentation (a.k.a. panoptic segmentation) consisting of a convolutional neural network and an asymmetric multiway cut problem solver. The latter solves a combinatorial optimization problem that elegantly incorporates semantic and boundary predictions to produce a panoptic labeling. Our formulation allows to directly maximize a smooth surrogate of the panoptic quality metric by backpropagating the gradient through the optimization problem. Experimental evaluation shows improvement by backpropagating through the optimization problem w.r.t. comparable approaches on Cityscapes and COCO datasets. Overall, our approach shows the utility of using combinatorial optimization in tandem with deep learning in a challenging large scale real-world problem and showcases benefits and insights into training such an architecture.
翻译:我们提出一个完全不同的同时语义和实例分割结构(a.k.a.a.panopic sectionation),由一个卷发神经网络和一个不对称的多路截断问题解答器组成。后者解决了一个组合优化问题,它优雅地结合语义和边界预测来制作一个全光标签。我们的配方能够通过通过优化问题对梯度进行反射,从而直接最大限度地实现全光质量指标的平稳替代。实验评估表明,通过对城市景景和COCO数据集的优化问题进行反射,通过对优化问题(w.r.t.)的可比方法进行反射,取得了改进。总体而言,我们的方法表明,在应对大规模现实世界问题时,在深刻学习的同时使用组合优化,可以同时产生巨大的学习,并展示培训这种结构的好处和洞察力。