AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network

Mei Wang, Weihong Deng, Jiani Hu, Xunqiang Tao, Yaohai Huang

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 375 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 clustering-based pseudo-label pre-adaptation (ablation)IMAN-A · RFW African target (6000 pairs)verification accuracy (%): 85.52 -> 88.12Improved
add MI loss on top of pseudo-adaptation (ablation)IMAN-A · RFW Indian target (6000 pairs)verification accuracy (%): 92.08 -> 93.55Improved
add MI loss on top of pseudo-adaptation (ablation)IMAN-A · RFW African target (6000 pairs)verification accuracy (%): 88.12 -> 88.88Improved
add MI loss on top of pseudo-adaptation (ablation)IMAN-A · RFW Asian target (6000 pairs)verification accuracy (%): 88.80 -> 89.87Improved
add pseudo-label adaptation to MI-only adaptation (MI alone with random classifier) (ablation)IMAN-A · RFW Asian target (6000 pairs)verification accuracy (%): 86.88 -> 89.87Improved
use IMAN-A instead of Arcface baselineArcface (CASIA source) · RFW African target (6000 pairs)verification accuracy (%): 85.13 -> 88.88Improved
replace Softmax with Arcface loss in pre-adaptation stage (IMAN*-A)IMAN-A · RFW African target (6000 pairs)verification accuracy (%): 88.88 -> 91.42Improved
use MMD-based DAN-A instead of plain ArcfaceArcface · RFW African target (6000 pairs)verification accuracy (%): 85.13 -> 86.30Improved
train on race-balanced Equalizedface instead of CASIA-WebFaceArcface ResNet-34 · RFW African (6000 pairs)verification accuracy (%): 84.93 -> 90.98Improved
train on race-balanced Equalizedface instead of CASIA-WebFaceArcface ResNet-34 · CFP-FPaccuracy (%): 93.91 -> 92.74Hurt
train on single-race 7000 identities instead of balanced 3.5K per race (Asian)Arcface ResNet-34 · RFW Asian (6000 pairs)verification accuracy (%): 90.60 -> 91.27Mixed
apply IMAN-A adaptation (CASIA to GBU) instead of ArcfaceArcface(CASIA) · GBU UglyVR at FAR 0.001 (%): 75.00 -> 85.38Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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