Robust Feature Rectification of Pretrained Vision Models for Object Recognition

Shengchao Zhou, Gaofeng Meng*, Zhaoxiang Zhang, Richard Yi Da Xu, Shiming Xiang

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

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.
Original languageEnglish
Title of host publicationProceedings of 37th AAAI Conference on Artificial Intelligence, AAAI 2023
EditorsBrian Williams, Yiling Chen, Jennifer Neville
Place of PublicationWashington, DC
PublisherAAAI press
Pages3796-3804
Number of pages9
Edition1st
ISBN (Electronic)9781577358800
DOIs
Publication statusPublished - 27 Jun 2023
Event37th AAAI Conference on Artificial Intelligence, AAAI 2023 and the 35th Conference on Innovative Applications of Artificial Intelligence, IAAI 2023 - Washington, United States
Duration: 7 Feb 202314 Feb 2023
https://ojs.aaai.org/index.php/AAAI/issue/view/553
https://aaai-23.aaai.org/

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
Number3
Volume37
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

Conference37th AAAI Conference on Artificial Intelligence, AAAI 2023 and the 35th Conference on Innovative Applications of Artificial Intelligence, IAAI 2023
Country/TerritoryUnited States
CityWashington
Period7/02/2314/02/23
Internet address

Scopus Subject Areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Robust Feature Rectification of Pretrained Vision Models for Object Recognition'. Together they form a unique fingerprint.

Cite this