InstanceCut: from Edges to Instances with MultiCut

Abstract

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 instance-aware 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.

The code would be released at https://github.com/alexander-kirillov/InstanceCut

References in corpus (5)

• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Fully Connected Deep Structured Networks
• Simultaneous Detection and Segmentation
• Pixel-wise Deep Learning for Contour Detection
• Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications

Cited by in corpus (6)

• Semantic Instance Segmentation with a Discriminative Loss Function
• Semantic Instance Segmentation via Deep Metric Learning
• Fast Scene Understanding for Autonomous Driving
• Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation
• Semantic Segmentation and Object Detection Towards Instance Segmentation: Breast Tumor Identification
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey