A dual-network progressive approach to weakly supervised object detection

Dong, X; Meng, D; Ma, F; Yang, Y

A dual-network progressive approach to weakly supervised object detection

Dong, X

Meng, D Ma, F Yang, Y

Permalink

Publication Type:: Conference Proceeding
Citation:: MM 2017 - Proceedings of the 2017 ACM Multimedia Conference, 2017, pp. 279 - 287
Issue Date:: 2017-10-23

Closed Access

	Filename	Description	Size
	p279-dong.pdf	Published version	2.26 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	Dong, X https://orcid.org/0000-0001-9272-1590	en_US
dc.contributor.author	Meng, D	en_US
dc.contributor.author	Ma, F	en_US
dc.contributor.author	Yang, Y https://orcid.org/0000-0001-5528-0546	en_US
dc.date.issued	2017-10-23	en_US
dc.identifier.citation	MM 2017 - Proceedings of the 2017 ACM Multimedia Conference, 2017, pp. 279 - 287	en_US
dc.identifier.isbn	9781450349062	en_US
dc.identifier.uri	http://hdl.handle.net/10453/127166
dc.description.abstract	© 2017 ACM. A major challenge that arises in Weakly Supervised Object Detection (WSOD) is that only image-level labels are available, whereas WSOD trains instance-level object detectors. A typical approach to WSOD is to 1) generate a series of region proposals for each image and assign the image-level label to all the proposals in that image; 2) train a classifier using all the proposals; and 3) use the classifier to select proposals with high confidence scores as the positive instances for another round of training. In this way, the image-level labels are iteratively transferred to instance-level labels. We aim to resolve the following two fundamental problems within this paradigm. First, existing proposal generation algorithms are not yet robust, thus the object proposals are often inaccurate. Second, the selected positive instances are sometimes noisy and unreliable, which hinders the training at subsequent iterations. We adopt two separate neural networks, one to focus on each problem, to better utilize the specific characteristic of region proposal refinement and positive instance selection. Further, to leverage the mutual benefits of the two tasks, the two neural networks are jointly trained and reinforced iteratively in a progressive manner, starting with easy and reliable instances and then gradually incorporating difficult ones at a later stage when the selection classifier is more robust. Extensive experiments on the PASCAL VOC dataset show that our method achieves state-of-the-art performance.	en_US
dc.relation.ispartof	MM 2017 - Proceedings of the 2017 ACM Multimedia Conference	en_US
dc.relation.isbasedon	10.1145/3123266.3123455	en_US
dc.title	A dual-network progressive approach to weakly supervised object detection	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
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 - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney/Students
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2017 ACM. A major challenge that arises in Weakly Supervised Object Detection (WSOD) is that only image-level labels are available, whereas WSOD trains instance-level object detectors. A typical approach to WSOD is to 1) generate a series of region proposals for each image and assign the image-level label to all the proposals in that image; 2) train a classifier using all the proposals; and 3) use the classifier to select proposals with high confidence scores as the positive instances for another round of training. In this way, the image-level labels are iteratively transferred to instance-level labels. We aim to resolve the following two fundamental problems within this paradigm. First, existing proposal generation algorithms are not yet robust, thus the object proposals are often inaccurate. Second, the selected positive instances are sometimes noisy and unreliable, which hinders the training at subsequent iterations. We adopt two separate neural networks, one to focus on each problem, to better utilize the specific characteristic of region proposal refinement and positive instance selection. Further, to leverage the mutual benefits of the two tasks, the two neural networks are jointly trained and reinforced iteratively in a progressive manner, starting with easy and reliable instances and then gradually incorporating difficult ones at a later stage when the selection classifier is more robust. Extensive experiments on the PASCAL VOC dataset show that our method achieves state-of-the-art performance.

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

http://hdl.handle.net/10453/127166