Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation

Page view(s)
5
Checked on Sep 19, 2022
Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation
Title:
Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation
Other Titles:
IEEE Transactions on Multimedia
Publication Date:
31 December 2021
Citation:
Liu, W., Kong, X., Hung, T.-Y., & Lin, G. (2021). Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation. IEEE Transactions on Multimedia, 1–1. https://doi.org/10.1109/tmm.2021.3139459
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 object activation maps, we propose a region prototypical network (\textbf{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.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - AI Singapore Programme
Grant Reference no. : AISG-RP-2018-003

This research / project is supported by the Ministry of Education - MOE Tier-1
Grant Reference no. : RG28/18 (S)

This research / project is supported by the Ministry of Education - MOE Tier-1
Grant Reference no. : RG22/19 (S)

This research / project is supported by the Ministry of Education - MOE Tier-1
Grant Reference no. : RG95/20

This work is supported by the Delta-NTU Corporate Lab with funding support from Delta Electronics Inc. and the National Research Foundation (NRF) Singapore (SMA-RP10). National Natural Science Foundation of China (No.61902077).
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1520-9210
1941-0077
Files uploaded:

Files uploaded:

File Size Format Action
tmm-weakly-cross-final.pdf 5.27 MB PDF Request a copy