AI Paper Atlas

Research map / Detection and segmentation / CNN features

Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation

CVPR 2016 · Detection and segmentation › CNN features · approach: Joint detection and instance segmentation · 89 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
use 3-scale rather than 1-scale input (ablation)MPA · VOC 2012 segmentation valAP r: 60.3 -> 62.1Helped
use 3-scale rather than 1-scale input (ablation)MPA · VOC 2012 segmentation valAP r vol: 54.5 -> 56.5Helped
use 3-scale rather than 1-scale input (ablation)MPA · VOC 2012 segmentation valAP r: 54.6 -> 56.6Helped
use 3-scale input rather than 1-scale input (ablation)MPA · VOC 2012 SDS valAP rHelped
use 3-scale rather than 1-scale input (ablation)MPA · COCOmAP r @ IoU=[0.5 : 0.95]: 17.7/17.7 -> 20.1/20.4Helped
use 3-scale rather than 1-scale input (ablation)MPA · COCOmAP r @ IoU=0.5: 31.5/31.6 -> 35.4/35.6Helped
use 3-scale rather than 1-scale input (ablation)MPA · COCOmAP r @ IoU=0.75: 17.8/17.7 -> 20.4/20.7Helped
aggregate overlapping patch masks to infer instancesMPA · VOC 2012 segmentation valAP rHelped

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