AI Paper Atlas

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

Adversarially Learned Representations for Information Obfuscation and Inference

Martin Bertran, Natalia Martinez, Afroditi Papadaki, Qiang Qiu, Miguel Rodrigues, Galen Reeves, Guillermo Sapiro

ICML 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 39 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
tighten tolerance k from 0.5 to 0.2 (smaller allowed leakage) (ablation)adversarial filter · CelebA emotion, fixed estimatoremotion accuracy: 68.4% -> 51.9%Improved
tighten tolerance k from 0.5 to 0.2 (ablation)adversarial filter · CelebA gender detectiongender accuracy: 89.3% -> 83.9%Hurt
filter versus blacking out lower faceadversarial filter k=0.2 · CelebA gender detectiongender accuracy: 75.5% -> 83.9%Improved
filter versus blacking out full faceadversarial filter k=0.5 · CelebA gender detectiongender accuracy: 67.9% -> 89.3%Improved
tighten tolerance k from infinity to 0.5 (ablation)adversarial filter · FaceScrub consenting userstop-5 accuracy: 98.7% -> 97.6%No clear effect
retrain final dense layer of subject network (ablation)adversarial filter k=0.5 · FaceScrub subject verificationtop-5 accuracy: 93.5% -> 96.8%Improved
retrain final dense layer of subject network (ablation)adversarial filter k=0.1 · FaceScrub subject verificationtop-5 accuracy: 74.5% -> 89.6%Improved
adversarially trained versus natural-image emotion estimatoradversarial filter k=0.2 · CelebA emotionemotion accuracy: 51.9% -> 74.3%Mixed
nonlinear versus linear filterstochastic neural network filter · synthetic data tradeoffI(U;X|Y) vs I(S;Y) tradeoffImproved

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