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

The problem of algorithmic bias in machine learning has gained a lot ofattention in recent years due to its concrete and potentially hazardousimplications in society. In much the same manner, biases can also alter modernindustrial and safety-critical applications where machine learning are based onhigh dimensional inputs such as images. This issue has however been mostly leftout of the spotlight in the machine learning literature. Contrarily to societalapplications where a set of proxy variables can be provided by the common senseor by regulations to draw the attention on potential risks, industrial andsafety-critical applications are most of the times sailing blind. The variablesrelated to undesired biases can indeed be indirectly represented in the inputdata, or can be unknown, thus making them harder to tackle. This raises seriousand well-founded concerns towards the commercial deployment of AI-basedsolutions, especially in a context where new regulations clearly address theissues opened by undesired biases in AI. Consequently, we propose here to makean overview of recent advances in this area, firstly by presenting how suchbiases can demonstrate themselves, then by exploring different ways to bringthem to light, and by probing different possibilities to mitigate them. Wefinally present a practical remote sensing use-case of industrial Fairness.

A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis