AI Paper Atlas

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

PMAL: Open Set Recognition via Robust Prototype Mining

Jing Lu, Yunlu Xu, Hao Li, Zhanzhan Cheng, Yi Niu

AAAI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 55 citations (OpenAlex)

Read the paper

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 PMAL rather than RPL-WRNOpen-set recognition · TinyImageNetAUROC: 80.9 -> 83.1Improved
Use PMAL rather than RPL++Open-set recognition · ImageNet-LTAUROC: 55.2 -> 71.7Improved
Add high-quality prototype selection (ablation)PMAL prototype mining · TinyImageNetAUROC: 78.1 -> 81.6Improved
Add diversity filtering (ablation)PMAL prototype mining · TinyImageNetAUROC: 80.3 -> 81.9Improved
Add both high-quality selection and diversity filtering (ablation)PMAL prototype mining · TinyImageNetAUROC: 78.1 -> 81.9Improved
Use point-to-set distance instead of nearest-prototype distance (ablation)PMAL embedding optimization · TinyImageNetAUROC: +1.2%Improved
Increase prototype count from 1 to 10 (ablation)PMAL · TinyImageNetAUROC: 79.9 -> 83.1Improved
Vary initial model count from 2 to 6 (ablation)PMAL prototype mining · TinyImageNetAUROC: 83.1; 83.3; 83.2; 83.0; 83.3No clear effect
Vary the prototype threshold epsilon (ablation)PMAL prototype mining · TinyImageNetAUROC: 73.6; 78.1; 82.6; 83.1; 81.2Mixed
Vary the margin delta (ablation)PMAL embedding optimization · TinyImageNetAUROC: 80.9; 82.8; 83.1; 82.1; 80.5Mixed
Select prototypes using embedding topology robustness rather than probability (ablation)PMAL prototype mining · TinyImageNetAUROC: 79.3 -> 83.1Improved
Select prototypes using embedding topology robustness rather than deep ensembles (ablation)PMAL prototype mining · TinyImageNetAUROC: 80.5 -> 83.1Improved

Later papers that compared with this method

1 later accepted paper reports PMAL 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