InstanceCut: From edges to instances with MultiCut

TitleInstanceCut: From edges to instances with MultiCut
Publication TypeConference Paper
Year of Publication2017
AuthorsKirillov, A, Levinkov, E, Andres, B, Savchynskyy, B, Rother, C
Conference NameProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
ISBN Number9781538604571

This work addresses the task of instance-aware semantic segmentation. Our key motivation is to design a simple method with a new modelling-paradigm, which therefore has a different trade-off between advantages and disadvantages compared to known approaches.Our approach, we term InstanceCut, represents the problem by two output modalities: (i) an instance-agnostic semantic segmentation and (ii) all instance-boundaries. The former is computed from a standard convolutional neural network for semantic segmentation, and the latter is derived from a new instanceaware edge detection model. To reason globally about the optimal partitioning of an image into instances, we combine these two modalities into a novel MultiCut formulation. We evaluate our approach on the challenging CityScapes dataset. Despite the conceptual simplicity of our approach, we achieve the best result among all published methods, and perform particularly well for rare object classes.

Citation KeyKirillov2017a