AI Paper Atlas

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

Amodal Instance Segmentation

Ke Li, Jitendra Malik

ECCV 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 163 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
train on synthetic occlusion for amodal masks instead of modal segmentation (IIS)Faster R-CNN pipeline · 100 annotated VOC objectsmAP^r at 50% IoU: 34.1 -> 45.2Improved
train on synthetic occlusion for amodal masks instead of modal segmentation (IIS)Faster R-CNN pipeline · 100 annotated VOC objectsmAP^r at 70% IoU: 14.0 -> 22.6Improved
amodal model instead of IIS with GT boxessegmentation · 100 annotated VOC objectsaccuracy at IoU 50%: 68.0 -> 80.0Improved
amodal model instead of IIS with GT boxessegmentation · 100 annotated VOC objectsarea under accuracy curve: 57.5 -> 64.3Improved
amodal model instead of IISFaster R-CNN pipeline · PASCAL 3D+ rigid objectsmAP^r at 50% IoU: 37.4 -> 44.0Improved
amodal model instead of IISFaster R-CNN pipeline · PASCAL 3D+ rigid objectsmAP^r at 70% IoU: 15.9 -> 20.9Improved
add modal segmentation heatmap as input (ablation)proposed method · 100 annotated VOC objectsmAP^r at 50% IoU: 35.2 -> 45.2Improved
add modal segmentation heatmap as input (ablation)proposed method · 100 annotated VOC objectsmAP^r at 70% IoU: 18.4 -> 22.6Improved
add dynamic sample generation of varied occlusions (ablation)proposed method · 100 annotated VOC objectsmAP^r at 50% IoU: 39.8 -> 45.2Improved
add dynamic sample generation of varied occlusions (ablation)proposed method · 100 annotated VOC objectsmAP^r at 70% IoU: 22.7 -> 22.6No 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