AI Paper Atlas

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

Pairwise Similarity Learning is SimPLE

Yandong Wen, Weiyang Liu, Yao Feng, Bhiksha Raj, Rita Singh, Adrian Weller, Michael J. Black, Bernhard Schölkopf

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 12 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
use reverse-direction hard pair mining (r=3) instead of r=1 (vanilla BCE) (ablation)SimPLE · Face validation setEER (%): 3.72 -> 3.23Improved
use generalized inner product with angular bias instead of cosine similarity (ablation)SimPLE · Face validation setEER (%): 4.81 -> 3.23Improved
use generalized inner product instead of cosine in SimPLE (ablation)SimPLE SFNet-20 · IJB-B 1:1 TAR@FAR=1e-5TAR (%): 63.09 -> 84.51Improved
apply generalized inner product (angular bias) to proxy-based cross-entropy (ablation)proxy-based CE loss · Setting A validationEER (%): 6.13 (CE) vs 5.99 to 9.83 across b_thetaNo clear effect
add angular margin with generalized inner product to CosFaceCosFace · Setting AconvergenceHurt
drop proxies, angular similarity and margin (SimPLE vs SphereFace2) in small settingSimPLE · IJB-B 1:1 TAR@FAR=1e-5 (SFNet-20)TAR (%): 77.13 -> 84.51Improved
use SimPLE with a stronger backbone and larger data (IResNet-100, MS1MV2) versus AdaFaceSimPLE · IJB-B 1:1 TAR@FAR=1e-4TAR (%): 94.78 vs AdaFace 95.67Mixed
replace softmax-based losses with SimPLE for speaker verificationResNet-34 · VoxCeleb1EER (%): 2.11 -> 1.85Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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