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

Despite the rapid progress in deep visual recognition, modern computer visiondatasets significantly overrepresent the developed world and models trained onsuch datasets underperform on images from unseen geographies. We investigatethe effectiveness of unsupervised domain adaptation (UDA) of such models acrossgeographies at closing this performance gap. To do so, we first curate twoshifts from existing datasets to study the Geographical DA problem, anddiscover new challenges beyond data distribution shift: context shift, whereinobject surroundings may change significantly across geographies, andsubpopulation shift, wherein the intra-category distributions may shift. Wedemonstrate the inefficacy of standard DA methods at Geographical DA,highlighting the need for specialized geographical adaptation solutions toaddress the challenge of making object recognition work for everyone.

Can domain adaptation make object recognition work for everyone?