Logo image
Back
An improved approach to weakly supervised semantic segmentation
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
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

Metrics

86 Record Views
Logo image