AI Paper Atlas

Research map / Detection and segmentation / CNN features

Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection

CVPR 2016 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 49 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
Add ODP to FRCN while retaining softmax classification (ablation)FRCN with VGG · PASCAL VOC 2007 test (07+12)mAP: +2.3%Helped
Use CDP without ODP (ablation)FRCN with VGG · PASCAL VOC 2007 test (07+12)mAP: 70.0 -> 70.9; drops by 1.0%Hurt
Jointly fine-tune the network with DPBP (ablation)FRCN+CDP+ODP · PASCAL VOC 2007 test (07+12)mAP: 72.4 -> 73.4; about 1.0%Helped
Weight training samples by IoU instead of setting all weights to 1 (ablation)FRCN+CDP+ODP · PASCAL VOC 2007 test (07+12)mAP: 71.1 -> 73.4; about 2%Helped
Add CDP and ODP to FRCNFRCN with VGG · PASCAL VOC 2007 test (07)mAP: 66.9 -> 71.1; 3%Helped
Add CDP and ODP to FRCNFRCN with VGG · PASCAL VOC 2012 test (12)mAP: 65.7 -> 66.9; 2%Helped

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