AI Paper Atlas

Research map / Detection and segmentation / CNN features

Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection

Hongyang Li, Yu Liu, Wanli Ouyang, Xiaogang Wang

IJCV 2018 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 92 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
split anchors across three layers instead of all at last feature map (ablation)zoom-out proposal network · PASCAL VOC region proposalsAR@100: 62.31 -> 65.98Improved
add zoom-in (deconvolution) path to the zoom-out network (ablation)ZIP · PASCAL VOC region proposalsAR@100: 65.98 -> 68.51Improved
place all anchors densely at every layer instead of splitting them (ablation)zoom-out_sp · PASCAL VOC region proposalsAR@100: 65.98 -> 66.02No clear effect
stack to 40 layers via zoom-out only instead of zoom-in (ablation)zoom-out_sp · PASCAL VOC region proposalsAR@100: 68.51 -> 67.21Hurt
add dynamic alternation of training input scale (ablation)ZIP · PASCAL VOC region proposalsAR@100: 68.51 -> 72.58Improved
add equilibrium training strategy (ablation)ZIP · PASCAL VOC region proposalsAR@100: 68.51 -> 69.85Improved
add gray-class training strategy (ablation)ZIP · PASCAL VOC region proposalsAR@100: 68.51 -> 69.77Improved
add MAD unit on top of all training strategies (ablation)ZIP + all · PASCAL VOC region proposalsAR@100: 74.22 -> 76.51Improved
use spatial MAD instead of channel-wise MAD (ablation)ZIP + all + MAD · PASCAL VOC region proposalsAR@100: 76.51 -> 76.50No clear effect
replace MAD with SENet excitation recalibration (ablation)ZIP + all · PASCAL VOC region proposalsAR@100: 76.51 -> 71.87Hurt
add zoom-in structure to zoom-out detector (ablation)ZIP detector · PASCAL VOC 2007 testmAP: 71.3 -> 73.1Improved
add MAD unit to ZIP detector (ablation)ZIP baseline · PASCAL VOC 2007 testmAP: 73.1 -> 76.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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