Harvesting information from captions for weakly supervised semantic segmentation

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Since acquiring pixel-wise annotations for training convolutional neural networks for semantic image segmentation is time-consuming, weakly supervised approaches that only require class tags have been proposed. In this work, we propose another form of supervision, namely image captions as they can be found on the Internet. These captions have two advantages. They do not require additional curation as it is the case for the clean class tags used by current weakly supervised approaches and they provide textual context for the classes present in an image. To leverage such textual context, we deploy a multi-modal network that learns a joint embedding of the visual representation of the image and the textual representation of the caption. The network estimates text activation maps (TAMs) for class names as well as compound concepts, i.e. combinations of nouns and their attributes. The TAMs of compound concepts describing classes of interest substantially improve the quality of the estimated class activation maps which are then used to train a network for semantic segmentation. We evaluate our method on the COCO dataset where it achieves state of the art results for weakly supervised image segmentation.

Original languageEnglish
Title of host publication2019 International Conference on Computer Vision Workshops : ICCV 2019 : proceedings : 27 October-2 November 2019, Seoul, Korea
Number of pages10
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers Inc.
Publication date10.2019
Pages4481-4490
Article number9022140
ISBN (print)978-1-7281-5024-6
ISBN (electronic)978-1-7281-5023-9
DOIs
Publication statusPublished - 10.2019
Externally publishedYes
Event17th IEEE/CVF International Conference on Computer Vision Workshop - ICCVW 2019 - Seoul, Korea, Republic of
Duration: 27.10.201928.10.2019
Conference number: 17
https://iccv2019.thecvf.com/

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

    Research areas

  • Multimodal learning, Semantic segmentation, Weakly supervised learning, Weakly supervised semantic segmentation
  • Informatics

DOI