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.
Code (12)
Tasks
image-classificationImage ClassificationSegmentationSemantic SegmentationThermal Image SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Semantic Context Encoding for Accurate 3D Point Cloud Segmentation
Semantic context plays a significant role in image segmentation. However, few prior works have explored semantic contexts for 3D point cloud segmentation. In this paper, we propose a simple yet effective Point Context En…
Image SegmentationPoint Cloud SegmentationSegmentationSemantic SegmentationFeature-Fused Context-Encoding Network for Neuroanatomy Segmentation
Automatic segmentation of fine-grained brain structures remains a challenging task. Current segmentation methods mainly utilize 2D and 3D deep neural networks. The 2D networks take image slices as input to produce coarse…
SegmentationContextualising Implicit Representations for Semantic Tasks
Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises…
SegmentationSemantic SegmentationSIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixe…
Knowledge DistillationSegmentationSemantic Segmentationzero-shot-classification+2Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation
This paper presents a novel framework to integrate both semantic and instance contexts for panoptic segmentation. In existing works, it is common to use a shared backbone to extract features for both things (countable cl…
Panoptic SegmentationSegmentation