AI Paper Atlas

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

Learning Disentangled Representation for Fair Facial Attribute Classification via Fairness-aware Information Alignment

Sungho Park, Sunhee Hwang, Dohyung Kim, Hyeran Byun

AAAI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 44 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
disentangle representations into TAL, PAL, and MAL, align attribute information with decorrelation loss, and re-encode MAL for classificationFD-VAE · CelebA, attractiveness with male and young as protected attributesequal opportunity: 1.3; 3.7Improved
disentangle representations into TAL, PAL, and MAL, align attribute information with decorrelation loss, and re-encode MAL for classificationFD-VAE · UTK Face, ethnicity and age with gender as protected attributeequalized odds: 1.1; 2.9Improved
add decorrelation loss LDC to FFVAE (ablation)FFVAE on CelebA · CelebA, attractiveness with male as protected attributeequal opportunity: 15.0 -> 3.4Improved
add decorrelation loss LDC to FFVAE (ablation)FFVAE on CelebA · CelebA, attractiveness with male as protected attributeaccuracy: 62.2 -> 64.1Improved
add MAL to the decorrelation-loss representation (ablation)FD-VAE on CelebA · CelebA, attractiveness with male as protected attributeequalized odds: 5.7 -> 2.1Improved
add MAL to the decorrelation-loss representation (ablation)FD-VAE on CelebA · CelebA, attractiveness with male as protected attributeaccuracy: 64.1 -> 60.3Hurt
use MAL directly with TAL instead of re-encoding MAL (ablation)FD-VAE downstream classifier · CelebA, attractiveness with male as protected attributeaccuracy: 60.3 -> 67.1Improved
use MAL directly with TAL instead of re-encoding MAL (ablation)FD-VAE downstream classifier · CelebA, attractiveness with male as protected attributeequal opportunity: 1.8 -> 19.8Hurt
re-encode MAL to retain target information while excluding protected information (ablation)FD-VAE downstream classifier · CelebA, attractiveness with male as protected attributeequal opportunity: 19.8 -> 1.3Improved
apply the downstream re-encoding framework to FFVAE (ablation)FFVAE · CelebA, attractiveness with male as protected attributeaccuracy: 62.2 -> 63.5Improved
apply the downstream re-encoding framework to FFVAE (ablation)FFVAE · CelebA, attractiveness with male as protected attributeequal opportunity: 15.0 -> 15.3Hurt

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