Language:

Semantic Understanding of Scenes Through the ADE20K Dataset

International journal of computer vision, 2019-03, Vol.127 (3), p.302-321 [Peer Reviewed Journal]

Springer Science+Business Media, LLC, part of Springer Nature 2018 ;COPYRIGHT 2019 Springer ;International Journal of Computer Vision is a copyright of Springer, (2018). All Rights Reserved. ;ISSN: 0920-5691 ;EISSN: 1573-1405 ;DOI: 10.1007/s11263-018-1140-0

Full text available

Citations Cited by

Actions
1. Add to My Research
2. Remove from My Research
3. E-mail
4. Print
5. Permalink
6. Citation
7. EasyBib
8. EndNote
9. RefWorks
10. Delicious
11. Export RIS
12. Export BibTeX

Title:
Semantic Understanding of Scenes Through the ADE20K Dataset
Author: Zhou, Bolei ; Zhao, Hang ; Puig, Xavier ; Xiao, Tete ; Fidler, Sanja ; Barriuso, Adela ; Torralba, Antonio
Subjects: Annotations ; Artificial Intelligence ; Benchmarking ; Benchmarks ; Computer Imaging ; Computer Science ; Computer vision ; Data acquisition ; Data collection ; Image Processing and Computer Vision ; Image segmentation ; Pattern Recognition ; Pattern Recognition and Graphics ; Scene analysis ; Semantics ; State of the art ; Vision
Is Part Of: International journal of computer vision, 2019-03, Vol.127 (3), p.302-321
Description: Semantic understanding of visual scenes is one of the holy grails of computer vision. Despite efforts of the community in data collection, there are still few image datasets covering a wide range of scenes and object categories with pixel-wise annotations for scene understanding. In this work, we present a densely annotated dataset ADE20K , which spans diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts. Totally there are 25k images of the complex everyday scenes containing a variety of objects in their natural spatial context. On average there are 19.5 instances and 10.5 object classes per image. Based on ADE20K, we construct benchmarks for scene parsing and instance segmentation. We provide baseline performances on both of the benchmarks and re-implement state-of-the-art models for open source. We further evaluate the effect of synchronized batch normalization and find that a reasonably large batch size is crucial for the semantic segmentation performance. We show that the networks trained on ADE20K are able to segment a wide variety of scenes and objects.
Publisher: New York: Springer US
Language: English
Identifier: ISSN: 0920-5691
EISSN: 1573-1405
DOI: 10.1007/s11263-018-1140-0
Source: AUTh Library subscriptions: ProQuest Central

Back to results list


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

Semantic Understanding of Scenes Through the ADE20K Dataset

Springer Science+Business Media, LLC, part of Springer Nature 2018 ;COPYRIGHT 2019 Springer ;International Journal of Computer Vision is a copyright of Springer, (2018). All Rights Reserved. ;ISSN: 0920-5691 ;EISSN: 1573-1405 ;DOI: 10.1007/s11263-018-1140-0

Searching Remote Databases, Please Wait