AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

MFNet: Multi-Filter Directive Network for Weakly Supervised Salient Object Detection

Yongri Piao, Jian Wang, Miao Zhang, Huchuan Lu

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 111 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 a directive filter to a single pseudo label Y1 (ablation)saliency network trained on Y1 · DUTS-TestF-measure: 0.607 -> 0.698Improved
add a directive filter to a single pseudo label Y2 (ablation)saliency network trained on Y2 · DUTS-TestF-measure: 0.639 -> 0.684Improved
use multiple directive filters with both labels instead of a single filter on Y1 (ablation)MFNet · DUTS-TestF-measure: 0.698 -> 0.710Improved
fuse labels by averaging instead of using single label Y2 (ablation)saliency network · DUTS-TestF-measure: 0.639 -> 0.638No clear effect
fuse labels by union instead of single label Y2 (ablation)saliency network · DUTS-TestF-measure: 0.639 -> 0.637No clear effect
fuse labels by intersection instead of single label Y2 (ablation)saliency network · DUTS-TestF-measure: 0.639 -> 0.649Mixed
use a dual-decoder with two labels instead of single label Y1 (ablation)saliency network · DUTS-TestF-measure: 0.607 -> 0.670Improved
replace dual decoder with multiple directive filters (ablation)MFNet · DUTS-TestF-measure: 0.670 -> 0.710Improved
add self-supervision between directive filters (delta 0 to 2) (ablation)MFNet · DUTS-TestF-measure: 0.702 -> 0.710Improved
encourage filters to learn different cues (delta -2 instead of 2) (ablation)MFNet · DUTS-TestF-measure: 0.710 -> 0.679Hurt
raise self-supervision weight delta from 2 to 4 (ablation)MFNet · DUTS-TestF-measure: 0.710 -> 0.706Hurt
saliency decoder guided by filtered cues instead of a directive filter output P1 (ablation)MFNet · ECSSDF-measure: 0.842 -> 0.854Improved

Later papers that compared with this method

2 later accepted papers report MF-Net as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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