AI Paper Atlas

Research map / Detection and segmentation / CNN features

Mask R-CNN

Kaiming He, Georgia Gkioxari, Piotr Dollar, Ross Girshick

ICCV 2017 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 30,402 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 per-pixel sigmoid with binary loss (decoupled masks) instead of softmax (ablation)Mask R-CNN ResNet-50-C4 · COCO minival instance segmentationmask AP: 24.8 -> 30.3Improved
predict class-specific masks instead of class-agnostic (ablation)Mask R-CNN ResNet-50-C4 · COCO minival instance segmentationmask AP: 29.7 -> 30.3No clear effect
replace RoIPool with RoIAlign (stride 16) (ablation)Mask R-CNN ResNet-50-C4 · COCO minival instance segmentationmask AP: 26.9 -> 30.3Improved
replace RoIWarp with RoIAlign (ablation)Mask R-CNN ResNet-50-C4 · COCO minival instance segmentationmask AP: 27.2 -> 30.2Improved
use average instead of max pooling in RoIAlign (ablation)Mask R-CNN ResNet-50-C4 · COCO minival instance segmentationmask AP: 30.2 -> 30.3No clear effect
replace RoIPool with RoIAlign (stride 32) (ablation)Mask R-CNN ResNet-50-C5 · COCO minival instance segmentation (stride 32)mask AP: 23.6 -> 30.9Improved
add RoIAlign with FPN (ablation)Mask R-CNN FPN · COCO minival instance segmentationmask AP: +1.5 mask APImproved
use an FCN mask branch instead of MLP (ablation)Mask R-CNN ResNet-50-FPN · COCO minival instance segmentationmask AP: 31.5 -> 33.6Improved
train with the mask branch (multi-task) instead of box-only (ablation)Faster R-CNN, RoIAlign ResNet-101-FPN · COCO test-dev object detectionbox AP: 37.3 -> 38.2Improved
replace ResNet-101-FPN with ResNeXt-101-FPN (ablation)Mask R-CNN · COCO test-dev instance segmentationmask AP: 35.7 -> 37.1Improved
replace ResNet-101-C4 with ResNet-101-FPN (ablation)Mask R-CNN · COCO minival instance segmentationmask AP: 32.7 -> 35.4Improved
replace RoIPool with RoIAlign for keypoints (ablation)Mask R-CNN ResNet-50-FPN · COCO minival keypoint detectionkeypoint AP: 59.8 -> 64.2Improved

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