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

Although face recognition has made impressive progress in recent years, weignore the racial bias of the recognition system when we pursue a high level ofaccuracy. Previous work found that for different races, face recognitionnetworks focus on different facial regions, and the sensitive regions ofdarker-skinned people are much smaller. Based on this discovery, we propose anew de-bias method based on gradient attention, called Gradient AttentionBalance Network (GABN). Specifically, we use the gradient attention map (GAM)of the face recognition network to track the sensitive facial regions and makethe GAMs of different races tend to be consistent through adversarial learning.This method mitigates the bias by making the network focus on similar facialregions. In addition, we also use masks to erase the Top-N sensitive facialregions, forcing the network to allocate its attention to a larger facialregion. This method expands the sensitive region of darker-skinned people andfurther reduces the gap between GAM of darker-skinned people and GAM ofCaucasians. Extensive experiments show that GABN successfully mitigates racialbias in face recognition and learns more balanced performance for people ofdifferent races.

Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention