AI Paper Atlas

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

OIMNet++: Prototypical Normalization and Localization-Aware Learning for Person Search

Sanghoon Lee, Youngmin Oh, Donghyeon Baek, Junghyup Lee, Bumsub Ham

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 38 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 BatchNorm before L2 normalization (ablation)OIMNet (OIM loss) · PRW searchmAP: 42.0 -> 44.3Improved
replace BatchNorm with ProtoNorm (ablation)OIMNet (OIM loss) · PRW searchmAP: 44.3 -> 46.3Improved
add ProtoNorm without BatchNorm (ablation)OIMNet (OIM loss) · PRW searchmAP: 42.0 -> 46.3Improved
replace BatchNorm with ProtoNorm (ablation)OIMNet (OIM loss) · PRW reIDmAP: 46.6 -> 48.4Improved
replace OIM loss with LOIM loss (ablation)OIMNet with BatchNorm · PRW searchmAP: 44.3 -> 45.1Improved
replace OIM loss with LOIM loss (ablation)OIMNet with BatchNorm · PRW searchrank-1: 81.5 -> 82.9Improved
replace OIM loss with LOIM loss (ablation)OIMNet with ProtoNorm · PRW searchmAP: 46.3 -> 46.8Improved
replace OIM loss with LOIM loss (ablation)OIMNet with ProtoNorm · PRW searchrank-1: 82.7 -> 83.9Improved
replace OIM loss with LOIM loss (ablation)OIMNet with ProtoNorm · PRW reIDrank-1: 84.6 -> 86.2Improved
replace OIM loss with LOIM loss (ablation)OIMNet with BatchNorm · PRW reIDmAP: 46.6 -> 47.4Improved
combine ProtoNorm and LOIM loss (ablation)OIMNet · PRW searchmAP: 42.0 -> 46.8Improved
replace BatchNorm with ProtoNorm (ablation)OIMNet with LOIM loss · PRW reIDmAP: 47.4 -> 49.0Improved

Later papers that compared with this method

2 later accepted papers report OIMNet+ as a baseline in their results tables; 2 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