AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach

Proteek Chandan Roy, Vishnu Naresh Boddeti

CVPR 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 88 citations (OpenAlex)

Check 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
Replace minimizing sensitive-label likelihood with maximizing discriminator entropyAdversarial representation learning · Extended Yale Blighting accuracy: 57 -> 40Improved
Replace minimizing sensitive-label likelihood with maximizing discriminator entropyAdversarial representation learning · Extended Yale Bidentity accuracy: 89 -> 89No clear effect
Replace minimizing sensitive-label likelihood with maximizing discriminator entropyAdversarial representation learning · German creditsensitive attribute accuracy: 80.2% -> 72.7%Improved
Replace minimizing sensitive-label likelihood with maximizing discriminator entropyAdversarial representation learning · German credittarget accuracy: 74.4% -> 86.33%Improved
Replace minimizing sensitive-label likelihood with maximizing discriminator entropyAdversarial representation learning · Adult incomesensitive attribute accuracy: 67.7% -> 65.5%Improved
Replace minimizing sensitive-label likelihood with maximizing discriminator entropyAdversarial representation learning · Adult incometarget accuracy: 84.4% -> 84.6%No clear effect
Replace minimizing sensitive-label likelihood with maximizing discriminator entropyAdversarial representation learning · Mixture of four Gaussiansadversary accuracy: 70% -> 63%Improved
Replace minimizing sensitive-label likelihood with maximizing discriminator entropyAdversarial representation learning · CIFAR-100 superclass/fine classadversary entropy: 2.27 -> 2.27; 4.60 -> 4.60Mixed

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