AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning Globally Optimized Object Detector via Policy Gradient

Yongming Rao, Dahua Lin, Jiwen Lu, Jie Zhou

CVPR 2018 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 29 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
Apply policy-gradient global optimizationFaster R-CNN · COCO minivalmAP: 36.3 -> 38.3Improved
Apply policy-gradient global optimizationFaster R-CNN with FPN · COCO minivalmAP: 37.7 -> 39.5Improved
Add the cross-entropy term to policy-gradient training (ablation)Faster R-CNN with policy-gradient training · COCO minivalmAP: 37.6 -> 38.3Improved
Remove the cross-entropy term from joint policy-gradient training (ablation)Faster R-CNN · COCO minivalmAP: 38.3 -> 37.6Hurt
Use policy-gradient training without cross-entropy (ablation)Faster R-CNN · COCO minivalmAP: 36.3 -> 37.6Improved
Replace standard training with OHEMFaster R-CNN · COCO minivalmAP: 36.3 -> 36.9Improved
Use soft NMS at inference instead of greedy NMS (ablation)Faster R-CNN · COCO minivalmAP: 36.3 -> 36.9Improved

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