AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

CoupleFace: Relation Matters for Face Recognition Distillation

Jiaheng Liu, Haoyu Qin, Yichao Wu, Jinyang Guo, Ding Liang, Ke Xu

ECCV 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 27 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 FCD embedding alignment instead of classical KDMobileNetV2 student · IJB-C (TAR@FAR=1e-4)TAR: 86.12 -> 90.34 (IJB-B 1e-4); 89.03 -> 92.68 (IJB-C 1e-4)Improved
add mutual relation distillation (RAD) on top of FCDMobileNetV2 student · IJB-C (TAR@FAR=1e-5)TAR: 87.74 -> 89.57Improved
add mutual relation distillation (RAD) on top of FCDMobileNetV2 student · MegaFace (10^6 distractors)rank-1 accuracy: 93.65 -> 94.27Improved
add ArcFace loss finetuning stage (CoupleFace+)CoupleFace · IJB-B (TAR@FAR=1e-5)TAR: 84.63 -> 85.12Improved
add selection of only valid relations (teacher closer than student) (ablation)CoupleFace-A · IJB-B (TAR@FAR=1e-5)TAR: 83.68 -> 84.23Improved
add margin q to RAD loss (ablation)CoupleFace-B · IJB-B (TAR@FAR=1e-5)TAR: 84.23 -> 84.63Improved
add margin q to RAD loss (ablation)CoupleFace-B · IJB-C (TAR@FAR=1e-5)TAR: 88.99 -> 89.57Improved
add informative relation mining with memory bank instead of batch-only relations (ablation)CoupleFace-C · IJB-B (TAR@FAR=1e-5)TAR: 83.18 -> 84.63Improved
mine most similar identities instead of random K=100 identities (ablation)CoupleFace-D · IJB-C (TAR@FAR=1e-5)TAR: 89.04 -> 89.57Improved
add mining with feature bank instead of mini-batch relations (ablation)CoupleFace-E · IJB-B (TAR@FAR=1e-5)TAR: 83.32 -> 84.63Improved
use R-50 teacher instead of MBNet to generate prototype set (ablation)CoupleFace-MBN · IJB-B (TAR@FAR=1e-5)TAR: 83.91 -> 84.63Improved
use R-100 instead of R-50 to generate prototype set (ablation)CoupleFace · IJB-C (TAR@FAR=1e-5)TAR: 89.57 -> 89.58No clear effect

Later papers that compared with this method

1 later accepted paper reports CoupleFace as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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