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 contributionpeer-review


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
Number of pages9
ISBN (Electronic)9781577358800
Publication statusPublished - 27 Jun 2023
Event37th AAAI Conference on Artificial Intelligence, AAAI 2023 - Washington, United States
Duration: 7 Feb 202314 Feb 2023

Publication series

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


Conference37th AAAI Conference on Artificial Intelligence, AAAI 2023
Country/TerritoryUnited States
Internet address


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

Cite this