An improved approach to weakly supervised semantic segmentation

L. Xu; M. Bennamoun; F. Boussaid; S. An; F. Sohel

doi:10.1109/ICASSP.2019.8682788

Back

Conference paper

An improved approach to weakly supervised semantic segmentation

L. Xu, M. Bennamoun, F. Boussaid, S. An and F. Sohel

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019 (Brighton, United Kingdom, 12/05/2019–17/05/2019)

2019

DOI: https://doi.org/10.1109/ICASSP.2019.8682788

Files and links (1)

url

Link to Published Version *Subscription may be requiredView

Abstract

Weakly supervised semantic segmentation with image-level labels is of great significance since it alleviates the dependency on dense annotations. However, it is a challenging task as it aims to achieve a mapping from high-level semantics to low-level features. In this work, we propose a three-step method to bridge this gap. First, we rely on the interpretable ability of deep neural networks to generate attention maps with class localization information by back-propagating gradients. Secondly, we employ an off-the-shelf object saliency detector with an iterative erasing strategy to obtain saliency maps with spatial extent information of objects. Finally, we combine these two complementary maps to generate pseudo ground-truth images for the training of the segmentation network. With the help of the pre-trained model on the MS-COCO dataset and a multi-scale fusion method, we obtained mIoU of 62.1% and 63.3% on PASCAL VOC 2012 val and test sets, respectively, achieving new state-of-the-art results for the weakly supervised semantic segmentation task.

Details

Title: An improved approach to weakly supervised semantic segmentation
Authors/Creators: L. Xu (Author/Creator) - Software
M. Bennamoun (Author/Creator) - School of Computer Science and Software Engineering
F. Boussaid (Author/Creator) - Department of Physics, Mathematics and Informatics
S. An (Author/Creator) - School of Electrical Engineering, Computing and Mathematical Sciences
F. Sohel (Author/Creator) - School of Engineering and Information Technology
Publication Details: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Conference: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019 (Brighton, United Kingdom, 12/05/2019–17/05/2019)
Identifiers: 991005544828007891
Murdoch Affiliation: School of Engineering and Information Technology
Language: English
Resource Type: Conference paper

Metrics

86 Record Views