Robust Feature Rectification of Pretrained Vision Models for Object Recognition

Zhou, S; Meng, G; Zhang, Z; Xu, RYD; Xiang, S

Robust Feature Rectification of Pretrained Vision Models for Object Recognition

Zhou, S Meng, G Zhang, Z Xu, RYD Xiang, S

Permalink

Publisher:: Association for the Advancement of Artificial Intelligence (AAAI)
Publication Type:: Journal Article
Citation:: Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, 2023, 37, (3), pp. 3796-3804
Issue Date:: 2023-06-27

Closed Access

	Filename	Description	Size
	25492-Article Text-29555-1-2-20230626.pdf	Published version	1.06 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	Zhou, S
dc.contributor.author	Meng, G
dc.contributor.author	Zhang, Z
dc.contributor.author	Xu, RYD
dc.contributor.author	Xiang, S
dc.date.accessioned	2024-05-10T10:38:53Z
dc.date.available	2024-05-10T10:38:53Z
dc.date.issued	2023-06-27
dc.identifier.citation	Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, 2023, 37, (3), pp. 3796-3804
dc.identifier.isbn	9781577358800
dc.identifier.issn	2159-5399
dc.identifier.issn	2374-3468
dc.identifier.uri	http://hdl.handle.net/10453/178809
dc.description.abstract	Pretrained vision models for object recognition often suffer a dramatic performance drop with degradations unseen during training. In this work, we propose a RObust FEature Rectification module (ROFER) to improve the performance of pretrained models against degradations. Specifically, ROFER first estimates the type and intensity of the degradation that corrupts the image features. Then, it leverages a Fully Convolutional Network (FCN) to rectify the features from the degradation by pulling them back to clear features. ROFER is a general-purpose module that can address various degradations simultaneously, including blur, noise, and low contrast. Besides, it can be plugged into pretrained models seamlessly to rectify the degraded features without retraining the whole model. Furthermore, ROFER can be easily extended to address composite degradations by adopting a beam search algorithm to find the composition order. Evaluations on CIFAR-10 and Tiny-ImageNet demonstrate that the accuracy of ROFER is 5% higher than that of SOTA methods on different degradations.With respect to composite degradations, ROFER improves the accuracy of a pretrained CNN by 10% and 6% on CIFAR-10 and Tiny-ImageNet respectively.
dc.language	en
dc.publisher	Association for the Advancement of Artificial Intelligence (AAAI)
dc.relation.ispartof	Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
dc.relation.isbasedon	10.1609/aaai.v37i3.25492
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Robust Feature Rectification of Pretrained Vision Models for Object Recognition
dc.type	Journal Article
utslib.citation.volume	37
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	*
dc.date.updated	2024-05-10T10:38:52Z
pubs.issue	3
pubs.publication-status	Published
pubs.volume	37
utslib.citation.issue	3

Abstract:

Pretrained vision models for object recognition often suffer a dramatic performance drop with degradations unseen during training. In this work, we propose a RObust FEature Rectification module (ROFER) to improve the performance of pretrained models against degradations. Specifically, ROFER first estimates the type and intensity of the degradation that corrupts the image features. Then, it leverages a Fully Convolutional Network (FCN) to rectify the features from the degradation by pulling them back to clear features. ROFER is a general-purpose module that can address various degradations simultaneously, including blur, noise, and low contrast. Besides, it can be plugged into pretrained models seamlessly to rectify the degraded features without retraining the whole model. Furthermore, ROFER can be easily extended to address composite degradations by adopting a beam search algorithm to find the composition order. Evaluations on CIFAR-10 and Tiny-ImageNet demonstrate that the accuracy of ROFER is 5% higher than that of SOTA methods on different degradations.With respect to composite degradations, ROFER improves the accuracy of a pretrained CNN by 10% and 6% on CIFAR-10 and Tiny-ImageNet respectively.

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

http://hdl.handle.net/10453/178809