AI Paper Atlas

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

How Trustworthy are Performance Evaluations for Basic Vision Tasks?

Tran Thien Dat Nguyen, Hamid Rezatofighi, Ba‐Ngu Vo, Ba-Tuong Vo, Silvio Savarese, Ian D. Reid

TPAMI 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 37 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
average F1 over the whole IoU threshold range (M-full) instead of IoU 0.5 (ablation)F1 · Single-class detection sanity testranking error: 10.0 -> 2.15Improved
average mAP over IoU 0.5-0.95 (M-partial) instead of IoU 0.5 (ablation)mAP · Multi-class detection sanity testranking error: 10.0 -> 7.52Improved
use optimal IoU threshold instead of IoU 0.5 (ablation)mAP · Multi-class detection sanity testranking error: 10.0 -> 7.08Improved
average mAP over the whole IoU range (M-full) instead of IoU 0.5 (ablation)mAP · Multi-class detection sanity testranking error: 10.0 -> 3.62Improved
replace F1 at IoU 0.5 with OSPA metricF1 · Single-class detection sanity testranking error: 10.0 -> 1.97Improved
replace mAP at IoU 0.5 with OSPA metricmAP · Multi-class detection sanity testranking error: 10.0 -> 1.86Improved
replace MOTA at IoU 0.5 with OSPA metricMOTA · Multi-object tracking sanity testranking error: 5.18 -> 0.518Improved
use Hausdorff metric instead of OSPAOSPA · Single-class detection sanity testranking error: 1.97 -> 17.8Hurt
use EMD metric instead of OSPAOSPA · Multi-class detection sanity testranking error: 1.86 -> 2.80Hurt
use approximate truth reference instead of ground truth reference (ablation)OSPA (IoU) · Trackingranking error: 0.536 -> 0.611No clear effect
use approximate truth reference instead of ground truth reference (ablation)EMD (IoU) · Multi-class detectionranking error: 4.16 -> 4.48No clear effect
use un-normalized OSPA (remove division by object count) (ablation)OSPA · scenarios 1-10 dislocation testprediction errorHurt

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