AI Paper Atlas

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

Amodal Segmentation Based on Visible Region Segmentation and Shape Prior

Yuting Xiao, Yanyu Xu, Ziming Zhong, Weixin Luo, Jiawei Li, Shenghua Gao

AAAI 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 62 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
use visible-region features and category shape priors to infer amodal masksOur method · D2SA, KINS, COCOA clsAmodal AP: 64.85 -> 70.27; 30.71 -> 32.08; 34.72 -> 35.41Improved
add visible attention (ablation)Our method · D2SA; KINSAmodal AP: 66.67 -> 69.98; 31.61 -> 31.94Improved
add the reclassification regularizer (ablation)Our method · D2SA; KINSAmodal AP: 69.02 -> 69.98; 31.65 -> 31.94Improved
add shape-prior refinement (ablation)Our method · D2SA; KINSAmodal AP: 68.84 -> 69.98; 31.70 -> 31.94Improved
add shape-prior post-processing (ablation)Our method · D2SA; KINSAmodal AP: 68.15 -> 69.98; 31.87 -> 31.94Improved
add feature matching to both mask heads (ablation)Our method · D2SA; KINSAmodal AP: 69.98 -> 70.27; 31.94 -> 32.08Improved
use amodal attention instead of visible attention for amodal refinement (ablation)attention variants · D2SA; KINSAmodal AP: 64.55 vs 66.98; 31.18 vs 31.32Hurt
use refined rather than coarse visible attention for amodal refinement (ablation)attention variants · D2SA; KINSAmodal AP: 67.11 -> 67.33; 31.57 -> 31.69Improved

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