AI Paper Atlas

Research map / Detection and segmentation / CNN features

A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

Zhaowei Cai, Quanfu Fan, Rogerio S. Feris, Nuno Vasconcelos

ECCV 2016 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 1,625 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
add input upsampling (height 384 to 576) (ablation)MS-CNN · KITTI val Cars ModerateAP: 80.63 -> 88.14Improved
add input upsampling (height 384 to 576) (ablation)MS-CNN · KITTI val Pedestrians ModerateAP: 68.37 -> 70.77Improved
raise input height beyond 2x with deconvolution (576 to 768) (ablation)MS-CNN with deconvolution · KITTI val Cars ModerateAP: 89.12 -> 88.83No clear effect
replace random sampling with bootstrapping (ablation)MS-CNN h576 · KITTI val Pedestrians ModerateAP: 65.91 -> 70.77Improved
replace mixture sampling with bootstrapping (ablation)MS-CNN h576 · KITTI val Pedestrians ModerateAP: 70.49 -> 70.77No clear effect
add deconvolution feature upsampling (ablation)MS-CNN h384 · KITTI val Cars ModerateAP: 80.63 -> 87.93Improved
add deconvolution feature upsampling (ablation)MS-CNN h576 · KITTI val Pedestrians ModerateAP: 70.77 -> 72.49Improved
add context encoding (ablation)MS-CNN h576 · KITTI val Pedestrians ModerateAP: 70.77 -> 71.45Improved
add dimensionality reduction conv to context model (ablation)MS-CNN h576-ctx · KITTI val Pedestrians ModerateAP: 71.45 -> 72.13No clear effect
combine detectors at multiple layers instead of single det-8 layer (ablation)MS-CNN proposal network · KITTI val car recall (all scales)recall: 0.6486 -> 0.9611Improved
add detection sub-network multi-task training to proposal learning (ablation)MS-CNN · KITTI val proposal recallrecallImproved
MS-CNN versus 3DOPMS-CNN · KITTI test Pedestrians ModerateAP: 67.47 -> 73.70Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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