AI Paper Atlas

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

Semi-Siamese Training for Shallow Face Learning

Hang Du, Hailin Shi, Yuchi Liu, Jun Wang, Zhen Lei, Dan Zeng, Tao Mei

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 29 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 the prototype constraint (ablation)softmax on shallow data · BLUFR (shallow data)BLUFR verification rate (%): 27.05 -> 24.87Hurt
add the prototype constraint (ablation)Arc-softmax on shallow data · BLUFR (shallow data)BLUFR verification rate (%): 40.34 -> 40.08No clear effect
add the network constraint (ablation)softmax on shallow data · BLUFR (shallow data)BLUFR verification rate (%): 27.05 -> 30.65Improved
add the gallery queue (ablation)softmax on shallow data · BLUFR (shallow data)BLUFR verification rate (%): 27.05 -> 52.05Improved
add the gallery queue (ablation)AM-softmax on shallow data · BLUFR (shallow data)BLUFR verification rate (%): 33.23 -> 62.07Improved
combine network constraint and gallery queue (ablation)softmax on shallow data · BLUFR (shallow data)BLUFR verification rate (%): 52.05 -> 69.93Improved
use moving-average Semi-Siamese networks with gallery queue (full SST) (ablation)softmax on shallow data · BLUFR (shallow data)BLUFR verification rate (%): 69.93 -> 77.58Improved
full SST over plain training (ablation)AM-softmax on shallow data · BLUFR (shallow data)BLUFR verification rate (%): 33.23 -> 84.95Improved
full SST over plain training (ablation)A-softmax on shallow data · BLUFR (shallow data)BLUFR verification rate (%): 37.16 -> 80.65Improved
train on shallow instead of deep data (two images per ID) (ablation)softmax · LFW (MobileFaceNet)accuracy (%): 99.10 -> 92.64Hurt
apply SST on deep datasoftmax · BLUFR (deep data)BLUFR verification rate (%): 93.15 -> 94.56Improved
apply SST on deep dataArc-softmax · BLUFR (deep data)BLUFR verification rate (%): 95.29 -> 94.76No clear effect

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