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

Deep neural networks (DNNs), despite their impressive ability to generalizeover-capacity networks, often rely heavily on malignant bias as shortcutsinstead of task-related information for discriminative tasks. To address thisproblem, recent studies utilize auxiliary information related to the bias,which is rarely obtainable in practice, or sift through a handful of bias-freesamples for debiasing. However, the success of these methods is not alwaysguaranteed due to the unfulfilled presumptions. In this paper, we propose anovel method, Contrastive Debiasing via Generative Bias-transformation (CDvG),which works without explicit bias labels or bias-free samples. Motivated by ourobservation that not only discriminative models but also image translationmodels tend to focus on the malignant bias, CDvG employs an image translationmodel to transform one bias mode into another while preserving thetask-relevant information. Additionally, the bias-transformed views are setagainst each other through contrastive learning to learn bias-invariantrepresentations. Our method demonstrates superior performance compared to priorapproaches, especially when bias-free samples are scarce or absent.Furthermore, CDvG can be integrated with the methods that focus on bias-freesamples in a plug-and-play manner for additional enhancements, as demonstratedby diverse experimental results.

Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation