Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism

Yang, B; Deng, X; Shi, H; Li, C; Zhang, G; Xu, H; Zhao, S; Lin, L; Liang, X

Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism

Yang, B Deng, X Shi, H Li, C Zhang, G Xu, H Zhao, S Lin, L Liang, X

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, 2022-June, pp. 9245-9254
Issue Date:: 2022-09-27

Closed Access

	Filename	Description	Size
	Continual_Object_Detection_via_Prototypical_Task_Correlation_Guided_Gating_Mechanism.pdf	Published version	518.47 kB	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, B
dc.contributor.author	Deng, X
dc.contributor.author	Shi, H
dc.contributor.author	Li, C
dc.contributor.author	Zhang, G
dc.contributor.author	Xu, H
dc.contributor.author	Zhao, S
dc.contributor.author	Lin, L
dc.contributor.author	Liang, X
dc.date	2022-06-18
dc.date.accessioned	2023-06-28T01:53:24Z
dc.date.available	2023-06-28T01:53:24Z
dc.date.issued	2022-09-27
dc.identifier.citation	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, 2022-June, pp. 9245-9254
dc.identifier.isbn	978-1-6654-6946-3
dc.identifier.issn	1063-6919
dc.identifier.issn	2575-7075
dc.identifier.uri	http://hdl.handle.net/10453/170922
dc.description.abstract	Continual learning is a challenging real world problem for constructing a mature AI system when data are provided in a streaming fashion Despite recent progress in continual classification the researches of continual object detection are impeded by the diverse sizes and numbers of objects in each image Different from previous works that tune the whole network for all tasks in this work we present a simple and flexible framework for continual object detection via pRotOtypical taSk corrElaTion guided gaTing mechAnism ROSETTA Concretely a unified framework is shared by all tasks while task aware gates are introduced to automatically select sub models for specific tasks In this way various knowledge can be successively memorized by storing their corresponding sub model weights in this system To make ROSETTA automatically determine which experience is available and useful a prototypical task correlation guided Gating Diversity Controller GDC is introduced to adaptively adjust the diversity of gates for the new task based on class specific prototypes GDC module computes class to class correlation matrix to depict the cross task correlation and hereby activates more exclusive gates for the new task if a significant domain gap is observed Comprehensive experiments on COCO VOC KITTI Kitchen class incremental detection on VOC and sequential learning of four tasks show that ROSETTA yields state of the art performance on both task based and class based continual object detection 11Codes are available at https github com dkxocl ROSSETA
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
dc.relation.ispartof	IEEE/CVF Conference on Computer Vision and Pattern Recognition
dc.relation.ispartofseries	IEEE Conference on Computer Vision and Pattern Recognition
dc.relation.isbasedon	10.1109/cvpr52688.2022.00904
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism
dc.type	Conference Proceeding
utslib.citation.volume	2022-June
utslib.location.activity	New Orleans, LA, USA
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/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-06-28T01:53:23Z
pubs.finish-date	2022-06-24
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2022-06-18
pubs.volume	2022-June
dc.location	Piscataway, USA

Abstract:

Continual learning is a challenging real world problem for constructing a mature AI system when data are provided in a streaming fashion Despite recent progress in continual classification the researches of continual object detection are impeded by the diverse sizes and numbers of objects in each image Different from previous works that tune the whole network for all tasks in this work we present a simple and flexible framework for continual object detection via pRotOtypical taSk corrElaTion guided gaTing mechAnism ROSETTA Concretely a unified framework is shared by all tasks while task aware gates are introduced to automatically select sub models for specific tasks In this way various knowledge can be successively memorized by storing their corresponding sub model weights in this system To make ROSETTA automatically determine which experience is available and useful a prototypical task correlation guided Gating Diversity Controller GDC is introduced to adaptively adjust the diversity of gates for the new task based on class specific prototypes GDC module computes class to class correlation matrix to depict the cross task correlation and hereby activates more exclusive gates for the new task if a significant domain gap is observed Comprehensive experiments on COCO VOC KITTI Kitchen class incremental detection on VOC and sequential learning of four tasks show that ROSETTA yields state of the art performance on both task based and class based continual object detection 11Codes are available at https github com dkxocl ROSSETA

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

http://hdl.handle.net/10453/170922