English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The 2D object detection in clean images has been a well studied topic, butits vulnerability against adversarial attack is still worrying. Existing workhas improved robustness of object detectors by adversarial training, at thesame time, the average precision (AP) on clean images drops significantly. Inthis paper, we propose that using feature alignment of intermediate layer canimprove clean AP and robustness in object detection. Further, on the basis ofadversarial training, we present two feature alignment modules:Knowledge-Distilled Feature Alignment (KDFA) module and Self-Supervised FeatureAlignment (SSFA) module, which can guide the network to generate more effectivefeatures. We conduct extensive experiments on PASCAL VOC and MS-COCO datasetsto verify the effectiveness of our proposed approach. The code of ourexperiments is available at https://github.com/grispeut/Feature-Alignment.git.

Using Feature Alignment Can Improve Clean Average Precision And Adversarial Robustness In Object Detection