AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Predicting Visual Political Bias Using Webly Supervised Data and an Auxiliary Task

Christopher Thomas, Adriana Kovashka

IJCV 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train with latent text document embedding as privileged informationResNet political bias classifier · topic Vaccinesaverage performance (accuracy): 0.6768 -> 0.7422Improved
train with latent text document embedding as privileged informationResNet political bias classifier · topic Climate Changeaverage performance (accuracy): 0.6934 -> 0.7179Improved
train with latent text document embedding as privileged informationResNet political bias classifier · top-20 media sourcesaverage performance (accuracy): 0.697 -> 0.739Improved
train with latent text document embedding as privileged informationResNet political bias classifier · top-100 media sourcesaverage performance (accuracy): 0.690 -> 0.724Improved
train with latent text document embedding as privileged informationResNet political bias classifier · Sunaverage performance (accuracy): 0.627 -> 0.707Improved
train with latent text document embedding as privileged informationResNet political bias classifier · Breitbartaverage performance (accuracy): 0.527 -> 0.607Improved
train with latent text document embedding as privileged informationResNet political bias classifier · RevComaverage performance (accuracy): 0.875 -> 0.781Hurt
train with latent text document embedding as privileged informationResNet political bias classifier · Slateaverage performance (accuracy): 0.798 -> 0.793No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy