AI Paper Atlas

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

Fair Loss: Margin-Aware Reinforcement Learning for Deep Face Recognition

Bingyu Liu, Weihong Deng, Yaoyao Zhong, Mei Wang, Jiani Hu, Xunqiang Tao, Yaohai Huang

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 87 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 learned adaptive margin (Fair Loss) to CosFaceCosFace, 34-layer · MegaFace Challenge 1 verificationTAR (%): 89.15 -> 90.82Improved
add learned adaptive margin (Fair Loss) to ArcFaceArcFace, 34-layer · MegaFace Challenge 1 verificationTAR (%): 91.06 -> 92.89Improved
add learned adaptive margin (Fair Loss) to CosFaceCosFace, 18-layer · MegaFace Challenge 1 verificationTAR (%): 86.80 -> 89.14Improved
add learned adaptive margin (Fair Loss) to ArcFaceArcFace, 18-layer · YTFaccuracy (%): 93.36 -> 93.76Improved
add learned adaptive margin (Fair Loss) to CosFaceCosFace, 34-layer · LFWaccuracy (%): 99.32 -> 99.52Improved
use RL-learned margin strategy instead of margins inversely proportional to class size (MIP) (ablation)CosFace · MegaFace Challenge 1 verificationTAR (%): 91.21 -> 92.87Improved
use RL-learned margin strategy instead of variance-deciding margins (VDM) (ablation)CosFace · MegaFace Challenge 1 verificationTAR (%): 91.43 -> 92.87Improved
use RL-learned margin strategy instead of random margins (RM) (ablation)CosFace · MegaFace Challenge 1 verificationTAR (%): 91.36 -> 92.87Improved
use RL-learned margin strategy instead of rule-based or random margins (ablation)CosFace · MegaFace Challenge 1 rank-1rank-1 accuracy (%): 76.77 -> 77.45Mixed
use RL-learned margin strategy instead of rule-based margins (ablation)CosFace · YTFaccuracy (%): 95.4 -> 96.2Mixed
add Fair Loss to CosFace under the large MF2 protocolCosFace · MegaFace Challenge 2 rank-1rank-1 accuracy (%): 74.11 -> 79.41Improved
add Fair Loss to CosFace under the large MF2 protocolCosFace · MegaFace Challenge 2 verificationTAR (%): 86.77 -> 89.62Improved

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