Widening residual skipped network for semantic segmentation. Issue 10 (14th September 2017)

• Record Type: Journal Article
• Authors: Su, Wen; Wang, Zengfu
• Is Part Of: IET image processing. Volume 11:Issue 10(2017)
• Page Start: 880
• Page End: 887
• Publication Date: 2017-09-14
• Subjects: image segmentation -- image coding -- computer vision -- neural nets -- image classification -- image resolution; Cityscapes dataset -- PASCAL VOC 2012 semantic segmentation dataset -- resolution image -- low‐resolution encoder -- classification layer maps -- deep layer semantic features -- pixel‐wise classification layer -- decoder network -- residual skipped connections -- encoder network -- precise boundary localisation -- image segmentation -- computer vision systems -- deep convolutional neural networks -- residual skipped network; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2017.0070
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Over the past two years deep convolutional neural networks have pushed the performance of computer vision systems to soaring heights on semantic segmentation. In this study, the authors present a novel semantic segmentation method of using a deep fully convolutional neural network to achieve image segmentation results with more precise boundary localisation. The above segmentation engine is trainable, and consists of an encoder network with widening residual skipped connections and a decoder network with a pixel‐wise classification layer. Here the encoder network with widening residual skipped connections allows the combination of shallow layer features and deep layer semantic features, and the decoder network with classification layer maps the low‐resolution encoder features to full resolution image with pixel‐wise classification. The experimental results on PASCAL VOC 2012 semantic segmentation dataset and Cityscapes dataset show that the proposed method is effective and competitive.