AI Paper Atlas

Research map / Detection and segmentation / CNN features

IMP: Instance Mask Projection for High Accuracy Semantic Segmentation of Things

Cheng-Yang Fu, Tamara L. Berg, Alexander C. Berg

ICCV 2019 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 18 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 Instance Mask Projection (ablation)Panoptic-P2 · Varied Clothing (val)semantic mIOU: 37.14 -> 46.59Improved
add Instance Mask Projection (ablation)Panoptic-FPN · Varied Clothing (val)semantic mIOU: 45.01 -> 47.03Improved
add Instance Mask Projection (ablation)Panoptic-FPN · Varied Clothing (val)semantic mAcc: 57.08 -> 61.52Improved
add Instance Mask Projection (ablation)Panoptic-P2 · ModaNet (val)semantic mIOU: 65.93 -> 69.65Improved
add Instance Mask Projection without augmentation (ablation)Panoptic-FPN · Cityscapes valmIOU: 72.74 -> 74.09Improved
add Instance Mask Projection with all augmentations (ablation)Panoptic-FPN · Cityscapes valmIOU: 76.11 -> 77.49Improved
add multi-scale training (ablation)Panoptic-FPN with ColorJitter · Cityscapes valmIOU: 73.12 -> 75.99Improved
add hard bootstrapping with ratio 0.10 (ablation)Panoptic-FPN with ColorJitter · Cityscapes valmIOU: 73.12 -> 74.94Improved
add color jitter (ablation)Panoptic-FPN · Cityscapes valmIOU: 72.74 -> 73.12No clear effect
use IMP-projected Mask R-CNN masks directly instead of a semantic head (ablation)Mask R-CNN-IMP · Varied Clothing (val)semantic mIOU: 42.66 -> 43.91Improved
add IMP to stuff classes in Cityscapes (wall) (ablation)Panoptic-FPN · Cityscapes valper-class IOU: -1.6/-6.7Hurt
add IMP for Cityscapes thing classes (ablation)Panoptic-FPN · Cityscapes val (thing classes)mIOU: +4.2/+3.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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