Objects in Semantic Topology

Yang, S; Sun, P; Jiang, Y; Xia, X; Zhang, R; Yuan, Z; Wang, C; Luo, P; Xu, M

Objects in Semantic Topology

Yang, S Sun, P Jiang, Y Xia, X Zhang, R Yuan, Z Wang, C Luo, P Xu, M

Permalink

Publisher:: OpenReview
Publication Type:: Conference Proceeding
Citation:: ICLR 2022 - 10th International Conference on Learning Representations, 2022, pp. 1-12
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	2530_objects_in_semantic_topology.pdf	Published version	9.16 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Yang, S
dc.contributor.author	Sun, P
dc.contributor.author	Jiang, Y
dc.contributor.author	Xia, X
dc.contributor.author	Zhang, R
dc.contributor.author	Yuan, Z
dc.contributor.author	Wang, C
dc.contributor.author	Luo, P
dc.contributor.author	Xu, M https://orcid.org/0000-0001-9581-8849
dc.date	2022-04-25
dc.date.accessioned	2023-07-23T02:08:51Z
dc.date.available	2023-07-23T02:08:51Z
dc.date.issued	2022-01-01
dc.identifier.citation	ICLR 2022 - 10th International Conference on Learning Representations, 2022, pp. 1-12
dc.identifier.uri	http://hdl.handle.net/10453/171608
dc.description.abstract	A more realistic object detection paradigm, Open-World Object Detection, has arised increasing research interests in the community recently. A qualified open-world object detector can not only identify objects of known categories, but also discover unknown objects, and incrementally learn to categorize them when their annotations progressively arrive. Previous works rely on independent modules to recognize unknown categories and perform incremental learning, respectively. In this paper, we provide a unified perspective: Semantic Topology. During the life-long learning of an open-world object detector, all object instances from the same category are assigned to their corresponding pre-defined node in the semantic topology, including the 'unknown' category. This constraint builds up discriminative feature representations and consistent relationships among objects, thus enabling the detector to distinguish unknown objects out of the known categories, as well as making learned features of known objects undistorted when learning new categories incrementally. Extensive experiments demonstrate that semantic topology, either randomly-generated or derived from a well-trained language model, could outperform the current state-of-the-art open-world object detectors by a large margin, e.g., the absolute open-set error (the number of unknown instances that are wrongly labeled as known) is reduced from 7832 to 2546, exhibiting the inherent superiority of semantic topology on open-world object detection.
dc.language	en
dc.publisher	OpenReview
dc.relation.ispartof	ICLR 2022 - 10th International Conference on Learning Representations
dc.relation.ispartof	International Conference on Learning Representations
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Objects in Semantic Topology
dc.type	Conference Proceeding
utslib.location.activity	Virtual
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - INEXT - Innovation in IT Services and Applications
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-07-23T02:08:45Z
pubs.finish-date	2022-04-29
pubs.publication-status	Published
pubs.start-date	2022-04-25

Abstract:

A more realistic object detection paradigm, Open-World Object Detection, has arised increasing research interests in the community recently. A qualified open-world object detector can not only identify objects of known categories, but also discover unknown objects, and incrementally learn to categorize them when their annotations progressively arrive. Previous works rely on independent modules to recognize unknown categories and perform incremental learning, respectively. In this paper, we provide a unified perspective: Semantic Topology. During the life-long learning of an open-world object detector, all object instances from the same category are assigned to their corresponding pre-defined node in the semantic topology, including the 'unknown' category. This constraint builds up discriminative feature representations and consistent relationships among objects, thus enabling the detector to distinguish unknown objects out of the known categories, as well as making learned features of known objects undistorted when learning new categories incrementally. Extensive experiments demonstrate that semantic topology, either randomly-generated or derived from a well-trained language model, could outperform the current state-of-the-art open-world object detectors by a large margin, e.g., the absolute open-set error (the number of unknown instances that are wrongly labeled as known) is reduced from 7832 to 2546, exhibiting the inherent superiority of semantic topology on open-world object detection.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/171608