Open Vocabulary Scene Parsing
Author(s)
Zhao, Hang; Puig Fernandez, Xavier; Zhou, Bolei; Fidler, Sanja; Torralba, Antonio
DownloadAccepted version (5.491Mb)
Terms of use
Metadata
Show full item recordAbstract
Recognizing arbitrary objects in the wild has been a challenging problem due to the limitations of existing classification models and datasets. In this paper, we propose a new task that aims at parsing scenes with a large and open vocabulary, and several evaluation metrics are explored for this problem. Our approach is a joint image pixel and word concept embeddings framework, where word concepts are connected by semantic relations. We validate the open vocabulary prediction ability of our framework on ADE20K dataset which covers a wide variety of scenes and objects. We further explore the trained joint embedding space to show its interpretability. Keywords: streaming media; vocabulary; training; semantics; predictive models; visualization
Date issued
2017-12-25Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryJournal
2017 IEEE International Conference on Computer Vision (ICCV)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Zhao, Hang et al. "Open Vocabulary Scene Parsing." 2017 IEEE International Conference on Computer Vision (ICCV), October 2017, Venice, Italy, Institute of Electrical and Electronics Engineers (IEEE), December 2017 © 2017 IEEE
Version: Author's final manuscript
ISBN
9781538610329
9781538610336
ISSN
2380-7504