Murdoch University Research Repository

Welcome to the Murdoch University Research Repository

The Murdoch University Research Repository is an open access digital collection of research
created by Murdoch University staff, researchers and postgraduate students.

Learn more

An improved approach to weakly supervised semantic segmentation

Xu, L., Bennamoun, M., Boussaid, F., An, S. and Sohel, F. (2019) An improved approach to weakly supervised semantic segmentation. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019, 12 - 17 May 2019, Brighton, United Kingdom

Link to Published Version: https://doi.org/10.1109/ICASSP.2019.8682788
*Subscription may be required

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.

Item Type: Conference Paper
Murdoch Affiliation: School of Engineering and Information Technology
URI: http://researchrepository.murdoch.edu.au/id/eprint/51569
Item Control Page Item Control Page