id:"swepub:oai:DiVA.org:liu-190654"
Search: id:"swepub:oai:DiVA.org:liu-190654" > OW-DETR: Open-world...
- 1 of 1
- Previous record
- Next record
- To hitlist
OW-DETR: Open-world Detection Transformer
-
- Gupta, Akshita (author)
- Incept Inst Artificial Intelligence, U Arab Emirates
-
- Narayan, Sanath (author)
- Incept Inst Artificial Intelligence, U Arab Emirates
-
- Joseph, K. J. (author)
- IIT Hyderabad, India; Mohamed Bin Zayed Univ Artificial Intelligence, U Arab Emirates
- show more...
- show less...
- (creator_code:org_t)
- IEEE COMPUTER SOC, 2022
- 2022
- English.
- In: 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR). - : IEEE COMPUTER SOC. - 9781665469463 - 9781665469470 ; , s. 9225-9234
- Conference paper (peer-reviewed)
Abstract
Subject headings
Close
- Open-world object detection (OWOD) is a challenging computer vision problem, where the task is to detect a known set of object categories while simultaneously identifying unknown objects. Additionally, the model must incrementally learn new classes that become known in the next training episodes. Distinct from standard object detection, the OWOD setting poses significant challenges for generating quality candidate proposals on potentially unknown objects, separating the unknown objects from the background and detecting diverse unknown objects. Here, we introduce a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection. The proposed OW-DETR comprises three dedicated components namely, attention-driven pseudo-labeling, novelty classification and objectness scoring to explicitly address the aforementioned OWOD challenges. Our OW-DETR explicitly encodes multi-scale contextual information, possesses less inductive bias, enables knowledge transfer from known classes to the unknown class and can better discriminate between unknown objects and background. Comprehensive experiments are performed on two benchmarks: MS-COCO and PASCAL VOC. The extensive ablations reveal the merits of our proposed contributions. Further, our model outperforms the recently introduced OWOD approach, ORE, with absolute gains ranging from 1.8% to 3.3% in terms of unknown recall on MS-COCO. In the case of incremental object detection, OW-DETR outperforms the state-of-theart for all settings on PASCAL VOC. Our code is available at https://github.com/akshitac8/OW-DETR.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
- 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (Search for host publication in LIBRIS)
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Gupta, Akshita
- Narayan, Sanath
- Joseph, K. J.
- Khan, Salman
- Khan, Fahad
- Shah, Mubarak
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Computer and Inf ...
- and Computer Vision ...
- Articles in the publication
- 2022 IEEE/CVF CO ...
- By the university
- Linköping University
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
