An Improved Approach to Weakly Supervised Semantic Segmentation

Research output: Chapter in Book/Conference paperConference paper

1 Citation (Scopus)

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. © 2019 IEEE.
Original languageEnglish
Title of host publicationInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1897-1901
ISBN (Electronic)978-147998131-1
DOIs
Publication statusPublished - 2019
Event2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 12 May 201917 May 2019
Conference number: 44

Conference

Conference2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
Abbreviated titleICASSP 2019
CountryUnited Kingdom
CityBrighton
Period12/05/1917/05/19

Fingerprint Dive into the research topics of 'An Improved Approach to Weakly Supervised Semantic Segmentation'. Together they form a unique fingerprint.

  • Cite this

    Xu, L., Bennamoun, M., An, S., Boussaid, F., & Sohel, F. (2019). An Improved Approach to Weakly Supervised Semantic Segmentation. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 1897-1901). [8682788] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICASSP.2019.8682788