AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

One Metric to Measure Them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks

Kemal Öksüz, Barış Can Çam, Sinan Kalkan, Emre Akbaş

TPAMI 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation · 50 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
evaluate with oLRP Error instead of AP50 to account for localisationFaster R-CNN X101, Libra R-CNN, Guided Anchoring · COCO 2017 valdetector ranking: equal AP50 63.7Improved
use oLRP Error instead of APC to compare NAS-FPN and GHMoLRP Error · COCO 2017 valperformance gap: 1.1% -> 0.4%Improved
use oLRP components to separate ATSS and Faster R-CNN with equal APCoLRP Error · COCO 2017 valoLRP Error: oLRP prefers Faster R-CNN by 1.1%Improved
add PR curve interpolation to AP on the rare toaster class (ablation)APC · COCO toaster classAPC: 2.2% on average, up to 6.2%Hurt
switch evaluation API from Pascal API to COCO API (ablation)AP50 · Pascal 2007 testAP50: 81.3 -> 84.0Hurt
increase detections per image from 300 to 1K (ablation)AP / oLRP Error · LVIS v1.0AP: 2.6% AP vs 1.4% oLRP differenceMixed
increase detections per class from 1K to 20K (ablation)AP / oLRP Error · LVIS v1.0 (fixed AP)AP: 3.7% AP vs 1.5% oLRP differenceMixed
use stronger backbone R50 to X101Mask R-CNN · LVIS v1.0oLRP Error: 80.7 -> 77.5Improved
reduce RPN proposals from 200 to 30 (ablation)Faster R-CNN R101 · Open Images valoLRP Error: 79.2 -> 79.9Hurt
add repeat factor sampling with t=0.01 (ablation)Mask R-CNN R50 · LVIS v1.0oLRP Error: 86.2 -> 78.8Improved
tune NMS IoU threshold to 0.50 (ablation)Faster R-CNN R50 · COCOoLRP Error: 90.5 -> 69.1Improved
remove FN errors from LRP computation (ablation)LRP Error · COCO panoptic with COCO-stuffLRP Error: 77.5 -> 62.4Improved

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