Please use this identifier to cite or link to this item:
|Title:||Cross-image region mining with region prototypical network for weakly supervised segmentation||Authors:||Liu, Weide
|Keywords:||Engineering::Computer science and engineering||Issue Date:||2021||Source:||Liu, W., Kong, X., Hung, T. & Lin, G. (2021). Cross-image region mining with region prototypical network for weakly supervised segmentation. IEEE Transactions On Multimedia, 3139459-. https://dx.doi.org/10.1109/TMM.2021.3139459||Project:||SMA-RP10
|Journal:||IEEE Transactions on Multimedia||Abstract:||Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the classification objective and lack the ability to generalize. To improve the generality of the objective activation maps, we propose a region prototypical network (RPNet) to explore the cross-image object diversity of the training set. Similar object parts across images are identified via region feature comparison. Object confidence is propagated between regions to discover new object areas while background regions are suppressed. Experiments show that the proposed method generates more complete and accurate pseudo object masks, while achieving state-of-the-art performance on PASCAL VOC 2012 and MS COCO. In addition, we investigate the robustness of the proposed method on reduced training sets.||URI:||https://hdl.handle.net/10356/162959||ISSN:||1520-9210||DOI:||10.1109/TMM.2021.3139459||Rights:||© 2021 IEEE. All rights reserved.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||SCSE Journal Articles|
Updated on Feb 2, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.