Context Encoding for Semantic Segmentation

doi:doi:10.57702/4nk97ji6

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 cap-tures the semantic context of scenes and selectively highlights class-dependent featuremaps.

BibTex:

@dataset{Hang_Zhang_and_Kristin_Dana_and_Jianping_Shi_and_Zhongyue_Zhang_and_Xiaogang_Wang_and_Ambrish_Tyagi_and_Amit_Agrawal_2024,
    abstract = {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 cap-tures the semantic context of scenes and selectively highlights class-dependent featuremaps.},
    author = {Hang Zhang and Kristin Dana and Jianping Shi and Zhongyue Zhang and Xiaogang Wang and Ambrish Tyagi and Amit Agrawal},
    doi = {10.57702/4nk97ji6},
    institution = {No Organization},
    keyword = {'Context Encoding Module', 'Fully Convolutional Network', 'Semantic Segmentation'},
    month = {dec},
    publisher = {TIB},
    title = {Context Encoding for Semantic Segmentation},
    url = {https://service.tib.eu/ldmservice/dataset/context-encoding-for-semantic-segmentation},
    year = {2024}
}