Affinity Derivation and Graph Merge for Instance Segmentation
arXiv:1811.10870
Abstract
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance. In our scheme, we use two neural networks with similar structure. One is to predict pixel level semantic score and the other is designed to derive pixel affinities. Regarding pixels as the vertexes and affinities as edges, we then propose a simple yet effective graph merge algorithm to cluster pixels into instances. Experimental results show that our scheme can generate fine-grained instance mask. With Cityscapes training data, the proposed scheme achieves 27.3 AP on test set.
arXiv commentPublished in ECCV 2018
References in corpus (17)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Rethinking Atrous Convolution for Semantic Image Segmentation
- ParseNet: Looking Wider to See Better
- A Review on Deep Learning Techniques Applied to Semantic Segmentation
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Learning to Segment Object Candidates
- Stacked Hourglass Networks for Human Pose Estimation
- Deformable Convolutional Networks
- Semantic Instance Segmentation via Deep Metric Learning
- Simultaneous Detection and Segmentation
- Semantic Image Segmentation via Deep Parsing Network
- Proposal-free Network for Instance-level Object Segmentation
- Stacked Deconvolutional Network for Semantic Segmentation
- Instance-sensitive Fully Convolutional Networks
- MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
- Object Detection Free Instance Segmentation With Labeling Transformations
- Boundary-aware Instance Segmentation