AI Paper Atlas

Research map / Detection and segmentation / CNN features

InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting

Hao-Shu Fang, Jianhua Sun, Runzhong Wang, Minghao Gou, Yong-Lu Li, Cewu Lu

ICCV 2019 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 233 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 random object jittering (random InstaBoost)Mask R-CNN Res-50-FPN · COCO test-dev segmentationAP seg: 33.8 -> 35.5Improved
add appearance-consistency heatmap guidance on top of random jitter (ablation)Mask R-CNN Res-50-FPN · COCO test-dev segmentationAP seg: 35.5 -> 36.0Improved
add InstaBoost (heatmap guided)Mask R-CNN Res-101-FPN · COCO test-dev segmentationAP seg: 35.7 -> 37.9Improved
add InstaBoost (heatmap guided)Cascade R-CNN Res-101-FPN · COCO test-dev segmentationAP seg: 37.3 -> 39.5Improved
add InstaBoost (heatmap guided)Mask R-CNN Res-101-FPN · COCO test-dev detectionAP det: 38.2 -> 43.0Improved
add InstaBoost (heatmap guided)Mask R-CNN Res-50-FPN · VOCSDS segmentationAP seg: 38.88 -> 42.73Improved
replace appearance-guided placement with random paste (ablation)Mask R-CNN Res-50-FPN · COCO segmentationAP seg: 33.8 -> 32.7Hurt
replace appearance-guided placement with random paste (ablation)Mask R-CNN Res-50-FPN · VOC segmentationAP seg: 38.88 -> 37.58Hurt
use InstaBoost instead of a context-model augmentation (ablation)Mask R-CNN Res-101-FPN · COCO segmentationAP seg: 36.2 -> 37.9Improved
increase InstaBoost training cost (train speed)Mask R-CNN Res-101-FPN · COCOtrain speed s/iter: 1.68 -> 1.71No clear effect
set translation ratio to 1/15 instead of 1 (ablation)InstaBoost · COCO val segmentationAP seg: 34.51 -> 35.10Improved
narrow scaling range from 0.7-1.3 to 0.8-1.2 (ablation)InstaBoost · COCO val segmentationAP seg: 34.85 -> 35.10Improved

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