Context Encoding for Semantic Segmentation

Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous convolution, utilizing multi-scale features and refining boundaries. In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps... The proposed Context Encoding Module significantly improves semantic segmentation results with only marginal extra computation cost over FCN. Our approach has achieved new state-of-the-art results 51.7% mIoU on PASCAL-Context, 85.9% mIoU on PASCAL VOC 2012. Our single model achieves a final score of 0.5567 on ADE20K test set, which surpass the winning entry of COCO-Place Challenge in 2017. In addition, we also explore how the Context Encoding Module can improve the feature representation of relatively shallow networks for the image classification on CIFAR-10 dataset. Our 14 layer network has achieved an error rate of 3.45%, which is comparable with state-of-the-art approaches with over 10 times more layers. The source code for the complete system are publicly available. read more

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Results from the Paper


Ranked #15 on Semantic Segmentation on PASCAL VOC 2012 test (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semantic Segmentation ADE20K EncNet Validation mIoU 44.65 # 35
Test Score 55.67 # 6
Semantic Segmentation ADE20K val EncNet (ResNet-101) mIoU 44.65 # 38
Semantic Segmentation PASCAL Context EncNet (ResNet-101) mIoU 51.7 # 34
Semantic Segmentation PASCAL VOC 2012 test EncNet (ResNet-101) Mean IoU 82.9% # 28
Semantic Segmentation PASCAL VOC 2012 test EncNet Mean IoU 85.9% # 15

Methods