AI Paper Atlas

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

Fairness by Learning Orthogonal Disentangled Representations

Mhd Hasan Sarhan, Nassir Navab, Abouzar Eslami, Shadi Albarqouni

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 72 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
add orthogonal-disentangled representation learning vs plain classifierResNet-18 classifier · CIFAR-10sensitive accuracy: 0.2344 -> 0.1907Improved
add orthogonal-disentangled representation learning vs plain classifierResNet-18 classifier · CIFAR-100sensitive accuracy: 0.3069 -> 0.1447Improved
add orthogonal-disentangled representation learning vs plain classifierResNet-18 classifier · CIFAR-10target accuracy: 0.9775 -> 0.9725Hurt
add orthogonal-disentangled representation learning vs plain classifierResNet-18 classifier · CIFAR-100target accuracy: 0.7199 -> 0.7074Hurt
add orthogonal-disentangled learning vs Roy et al. at comparable target accuracyRoy et al. (trade-off #2) · CIFAR-100sensitive accuracy: 0.1643 -> 0.1447Improved
add entropy loss and KL with orthogonal means (full model) vs plain classifier (ablation)baseline classifier · five datasetssensitive accuracyImproved
add KL orthogonal loss without entropy loss (ablation)KL Orth. w/o Entropy · CIFAR-10sensitive accuracy: 0.26% drop in target performanceImproved
add entropy loss alone or KL loss alone vs multi-task learning (ablation)multi-task learning · ablation datasetssensitive accuracyNo clear effect
add auxiliary sensitive classifier (multi-task) to the target classifier (ablation)baseline classifier · three of five datasetssensitive accuracyImproved
add orthogonality to disentangled KL loss (orthogonal means instead of similar means) (ablation)Entropy + KL · ablation datasetssensitive accuracyImproved

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