AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

FairViT: Fair Vision Transformer via Adaptive Masking

Bowei Tian, Ruijie Du, Yanning Shen

ECCV 2024 · Architectures and efficiency › Attention and transformers · approach: Hybrid and interpretable ViT designs · 6 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 distance loss to cross-entropy (ablation)FairViT · CelebA (Y: Attraction, S: Gender)accuracy (%): 74.01 -> 77.01Improved
add static adaptive masks on top of distance loss (ablation)FairViT · CelebA (Y: Attraction, S: Gender)accuracy (%): 77.01 -> 79.96Improved
update masks and weights by gradient instead of keeping them static (ablation)FairViT · CelebA (Y: Attraction, S: Gender)accuracy (%): 79.96 -> 84.01Improved
update masks and weights by gradient instead of keeping them static (ablation)FairViT · CelebA (Y: Attraction, S: Gender)EO (e-2): 8.99 -> 1.15Improved
use static masks rather than none on fairness DP (ablation)FairViT · CelebA (Y: Attraction, S: Gender)DP (e-1): 3.166 -> 3.929Hurt
use FairViT instead of vanilla ViTFairViT · CelebA (Y: Attraction, S: Gender)EO (e-2): 14.43 -> 1.15Improved
use FairViT instead of FSCL+ for fairnessFairViT · CelebA (Y: Attraction, S: Gender)EO (e-2): 0.79 -> 1.15Hurt
use FairViT instead of FSCL+ for accuracyFairViT · CelebA (Y: Attraction, S: Gender)accuracy (%): 77.26 -> 84.01Improved
increase distance loss weight alpha from 0.01 to 1 (ablation)FairViT · CelebA (Y: Attraction, S: Gender)accuracy (%): 82.51 -> 75.53Hurt
add small distance loss weight alpha=0.01 versus 0 (ablation)FairViT · CelebA (Y: Attraction, S: Gender)accuracy (%): 81.08 -> 82.51Improved
increase gamma beyond 0.5 (ablation)FairViT · CelebA (Y: Attraction, S: Gender)accuracy (%): 82.75 -> 81.67Hurt
use FairViT instead of FSCL+ for training timeFairViT · CelebA (Y: Attraction, S: Gender)training time (min): 34.73 -> 5.09Improved

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