AI Paper Atlas

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

PROB: Probabilistic Objectness for Open World Object Detection

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 110 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 probabilistic class-agnostic objectness with a Gaussian embedding modelDeformable DETR for open-world detection · M-OWODB Tasks 1–3U-Recall: 7.5 -> 19.4; 6.2 -> 17.4; 5.7 -> 19.6Helped
Remove objectness likelihood maximization (ablation)PROB · M-OWODB Task 2mAP both known: 44.0 -> 32.3Hurt
Remove objectness likelihood maximization (ablation)PROB · M-OWODB Task 2U-Recall: 17.4 -> 18.9No clear effect
Remove active exemplar selection (ablation)PROB · M-OWODB Task 2U-Recall: 17.4 -> 15.9Hurt
Remove active exemplar selection (ablation)PROB · M-OWODB Task 2mAP both known: 44.0 -> 43.5Hurt
Set inference objectness temperature to 0.5PROB · M-OWODB Task 2A-OSE: 6452 -> 562Helped
Set inference objectness temperature to 0.5PROB · M-OWODB Task 2U-Recall: 17.4 -> 17.7No clear effect

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