TUTCRIS - Tampereen teknillinen yliopisto


Cross-Granularity Attention Network for Semantic Segmentation



Otsikko2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
ISBN (elektroninen)9781728150239
DOI - pysyväislinkit
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE/CVF International Conference on Computer Vision Workshop - Seoul, Etelä-Korea
Kesto: 27 lokakuuta 201928 lokakuuta 2019


NimiIEEE International Conference on Computer Vision workshops
ISSN (elektroninen)2473-9944


ConferenceIEEE/CVF International Conference on Computer Vision Workshop


Despite the remarkable progress of semantic segmentation in recent years, much remains to be addressed in order to achieve better semantic coherence and boundary delineation. In this paper, we propose a novel convolutional neural network (CNN) architecture for semantic segmentation which explicitly addresses these two issues. Specifically, we propose a categorical attention mechanism to propagate consistent category-oriented information across multi-granularity contextual interpretations to close the semantic gap residing in CNN feature hierarchy. This novel design alleviates the semantic information loss during the feature combination and transformation process in decoder network. We further integrate a contour branch in our architecture to enhance the boundary awareness of the semantic feature derived in the form of a novel element-wise contour attention at each level of feature hierarchy. Additionally, we introduce a cross-granularity contour enhancement mechanism to propagate rich boundary cues from early layers to deep layers. We perform extensive quantitative evaluations in close proximity to object boundaries which confirms its superior effectiveness in boundary delineation. These novel mechanisms which boost the essentials in segmentation, i.e., region-wise semantic coherence and accurate object contour localization, allow our architecture 'MeshNet' to obtain state-of-the-art performance on two challenging datasets, i.e., PASCAL VOC 2012 and Cityscapes.