Abstract
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through the use of contextual information, specifically, we explore 'patch-patch' context between image regions, and 'patch-background' context. For learning from the patch-patch context, we formulate Conditional Random Fields (CRFs) with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches. Efficient piecewise training of the proposed deep structured model is then applied to avoid repeated expensive CRF inference for back propagation. For capturing the patch-background context, we show that a network design with traditional multi-scale image input and sliding pyramid pooling is effective for improving performance. Our experimental results set new state-of-the-art performance on a number of popular semantic segmentation datasets, including NYUDv2, PASCAL VOC 2012, PASCAL-Context, and SIFT-flow. In particular, we achieve an intersection-overunion score of 78:0 on the challenging PASCAL VOC 2012 dataset.
Keywords
Computer scienceArtificial intelligenceConditional random fieldSegmentationCRFSConvolutional neural networkPascal (unit)PiecewiseInferenceDeep learningPattern recognition (psychology)Image segmentationMachine learningMathematics
Affiliated Institutions
Related Publications
Fully Convolutional Networks for Semantic Segmentation
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, im...
Fully convolutional networks for semantic segmentation
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, ex...
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification pr...
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical ...
Learning Deconvolution Network for Semantic Segmentation
We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer ne...
Publication Info
- Year
- 2016
- Type
- article
- Citations
- 844
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
844
OpenAlex
Cite This
Guosheng Lin,
Chunhua Shen,
Anton van den Hengel
et al.
(2016).
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation.
.
https://doi.org/10.1109/cvpr.2016.348
Identifiers
- DOI
- 10.1109/cvpr.2016.348