AI Paper Atlas

Research map / Detection and segmentation / CNN features

Multi-Scale Interactive Network for Salient Object Detection

Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu

CVPR 2020 · Detection and segmentation › CNN features · approach: RGB salient object detection · 861 citations (OpenAlex)

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 AIMs to the baseline network (ablation)MINet · DUTS-TEFavg: 0.738 -> 0.775Improved
add SIMs to the baseline network (ablation)MINet · DUTS-TEFavg: 0.738 -> 0.786Improved
combine AIMs and SIMs (ablation)MINet · DUTS-TEFavg: 0.775 -> 0.792Improved
add CEL to the AIMs+SIMs model (ablation)MINet · DUTS-TEFavg: 0.792 -> 0.823Improved
replace AIMs with Amulet-like fusion (ablation)MINet baseline · DUTS-TEFavg: 0.775 -> 0.758Hurt
replace SIMs with PPM (ablation)MINet baseline · DUTS-TEFavg: 0.786 -> 0.762Hurt
replace SIMs with ASPP (ablation)MINet baseline · DUTS-TEFavg: 0.786 -> 0.777Hurt
use MINet instead of CPDsalient object detection models · DUT-OMRONFavg: 0.745 -> 0.741Hurt
use MINet instead of CPDsalient object detection models · DUTS-TEFavg: 0.813 -> 0.823Improved

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