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

A number of studies point out that current Visual Question Answering (VQA)models are severely affected by the language prior problem, which refers toblindly making predictions based on the language shortcut. Some efforts havebeen devoted to overcoming this issue with delicate models. However, there isno research to address it from the angle of the answer feature space learning,despite of the fact that existing VQA methods all cast VQA as a classificationtask. Inspired by this, in this work, we attempt to tackle the language priorproblem from the viewpoint of the feature space learning. To this end, anadapted margin cosine loss is designed to discriminate the frequent and thesparse answer feature space under each question type properly. As a result, thelimited patterns within the language modality are largely reduced, thereby lesslanguage priors would be introduced by our method. We apply this loss functionto several baseline models and evaluate its effectiveness on two VQA-CPbenchmarks. Experimental results demonstrate that our adapted margin cosineloss can greatly enhance the baseline models with an absolute performance gainof 15\% on average, strongly verifying the potential of tackling the languageprior problem in VQA from the angle of the answer feature space learning.

AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss