atlas

Research map / Detection and segmentation / CNN features

You Only Look Once: Unified, Real-Time Object Detection

CVPR 2016 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 51,511 citations (OpenAlex)

Check 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
Replace YOLO's 24-layer network with the 9-layer Fast YOLO network and fewer filters (ablation)YOLO · Pascal VOC 2007mAP: 63.4 -> 52.7Hurt
Replace YOLO's 24-layer network with the 9-layer Fast YOLO network and fewer filters (ablation)YOLO · Pascal VOC 2007FPS: 45 -> 155Helped
Add YOLO-based rescoring of Fast R-CNN detectionsFast R-CNN · Pascal VOC 2007mAP: 71.8 -> 75.0; 3.2%Helped
Combine Fast R-CNN with another Fast R-CNN version instead of YOLOFast R-CNN · Pascal VOC 2007mAP: .3 to .6%Helped
Apply non-maximal suppression to remove duplicate detections (ablation)YOLO · Pascal VOCmAP: 2-3%Helped
Use YOLO rather than Fast R-CNN for detectionsobject detection · Pascal VOC 2007background false-positive rate: 13.6%; almost 3xHelped
Use YOLO rather than Fast R-CNN for localizationobject detection · Pascal VOC 2007localization errorsHurt

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