AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Interactive Boundary Prediction for Object Selection

Hoang Le, Long Mai, Brian Price, Scott Cohen, Hailin Jin, Feng Liu

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 40 citations (OpenAlex)

Read the paper

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
use interaction-adaptive predicted boundary map instead of RCF semantic edge mapgeodesic path boundary extraction · GrabCutF-score: 0.8027 -> 0.9134Improved
use interaction-adaptive predicted boundary map instead of RCF semantic edge mapgeodesic path boundary extraction · BSDSF-score: 0.7315 -> 0.7514Improved
use interaction-adaptive predicted boundary map instead of RCF semantic edge mapgeodesic path boundary extraction · GrabCutIU: 0.9084 -> 0.9158Improved
use interaction-adaptive predicted boundary map instead of RCF semantic edge mapgeodesic path boundary extraction · BSDSIU: 0.7310 -> 0.7411Improved
use adaptive predicted map instead of oracle-best Canny edge mapgeodesic path boundary extraction · GrabCutF-score: 0.6628 -> 0.9134Improved
use adaptive predicted map instead of oracle-best gradient mapgeodesic path boundary extraction · GrabCutF-score: 0.5770 -> 0.9134Improved
use adaptive predicted map instead of oracle-best gradient mapgeodesic path boundary extraction · BSDSF-score: 0.5210 -> 0.7514Improved
use adaptive predicted map instead of oracle-best Canny edge mapgeodesic path boundary extraction · BSDSF-score: 0.6060 -> 0.7514Improved
add the local selection-sensitive loss (ablation)boundary prediction network · GrabCut and BSDS interactive simulation (Fig. 6)F-score vs #clicksImproved
add the segmentation-aware loss (ablation)boundary prediction network · GrabCut and BSDS interactive simulation (Fig. 6)F-score vs #clicksImproved
add the global boundary loss (ablation)boundary prediction network · GrabCut and BSDS interactive simulation (Fig. 6)F-score vs #clicksImproved
perturb simulated control points with empirical user noiseboundary prediction network · GrabCut and BSDS (Fig. 10)F-score and IU vs #clicksNo clear effect

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