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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper describes a simple yet effective technique for refining apretrained classifier network. The proposed AdCorDA method is based onmodification of the training set and making use of the duality between networkweights and layer inputs. We call this input space training. The methodconsists of two stages - adversarial correction followed by domain adaptation.Adversarial correction uses adversarial attacks to correct incorrecttraining-set classifications. The incorrectly classified samples of thetraining set are removed and replaced with the adversarially corrected samplesto form a new training set, and then, in the second stage, domain adaptation isperformed back to the original training set. Extensive experimental validationsshow significant accuracy boosts of over 5% on the CIFAR-100 dataset. Thetechnique can be straightforwardly applied to refinement of weight-quantizedneural networks, where experiments show substantial enhancement in performanceover the baseline. The adversarial correction technique also results inenhanced robustness to adversarial attacks.

AdCorDA: Classifier Refinement via Adversarial Correction and Domain Adaptation