Scene Parsing with Global Context Embedding

Abstract

We present a scene parsing method that utilizes global context information based on both the parametric and non- parametric models. Compared to previous methods that only exploit the local relationship between objects, we train a context network based on scene similarities to generate feature representations for global contexts. In addition, these learned features are utilized to generate global and spatial priors for explicit classes inference. We then design modules to embed the feature representations and the priors into the segmentation network as additional global context cues. We show that the proposed method can eliminate false positives that are not compatible with the global context representations. Experiments on both the MIT ADE20K and PASCAL Context datasets show that the proposed method performs favorably against existing methods.

Accepted in ICCV'17. Code available at https://github.com/hfslyc/GCPNet

References in corpus (12)

• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Multi-Scale Context Aggregation by Dilated Convolutions
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• Pyramid Scene Parsing Network
• Unsupervised Visual Representation Learning by Context Prediction
• Unsupervised Learning of Visual Representations using Videos
• Semantic Image Segmentation via Deep Parsing Network
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection

Cited by in corpus (5)

• Semantic Correlation Promoted Shape-Variant Context for Segmentation
• Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects
• Dense Recurrent Neural Networks for Scene Labeling
• Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection
• Non-parametric spatially constrained local prior for scene parsing on real-world data