AI Paper Atlas

Research map / Detection and segmentation / CNN features

LevelSet R-CNN: A Deep Variational Method for Instance Segmentation

Namdar Homayounfar Yuwen Xiong Justin Liang Wei-Chiu Ma Raquel Urtasun {namdar, yuwen, justin.liang, weichiu, urtasun}@uber.com

ECCV 2020 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 33 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 the Chan-Vese level set module and extra headsMask R-CNN · Cityscapes valAP: 32.3 -> 36.2Improved
add the level set moduleMask R-CNN · COCO valAP: 33.8 -> 34.3Improved
add the level set moduleMask R-CNN · LVIS val (COCO categories)AP*: 35.6 -> 36.4Improved
run unrolled level set optimization on top of the initial mask (ablation)LevelSet R-CNN · Cityscapes valAP: 35.4 -> 36.2Improved
run unrolled level set optimization on top of the initial mask (ablation)LevelSet R-CNN · COCO valAP: 33.7 -> 34.3Improved
backpropagate the final TSDF loss through the initial TSDF head (ablation)LevelSet R-CNN · Cityscapes valfinal mask AP: 34.2 -> 36.2Improved
backpropagate the final TSDF loss through the initial TSDF head (ablation)LevelSet R-CNN · Cityscapes valinitial mask AP: 33.0 -> 35.4Improved
add instance-adaptive hyperparameter head instead of global hyperparameters (ablation)LevelSet R-CNN · Cityscapes valAP: 35.4 -> 36.2Improved
use region-based Chan-Vese module instead of level set lossMask R-CNN · Cityscapes valAP: 34.3 -> 36.2Improved
use region-based Chan-Vese module instead of DELSE edge-based level setMask R-CNN · Cityscapes valAP: 35 -> 36.2Improved
train mask head with TSDF loss only, without Chan-Vese components (ablation)Mask R-CNN · Cityscapes valAP: 32.3 -> 32.3No clear effect
increase Mask R-CNN mask head resolution to 112x112Mask R-CNN · Cityscapes valAP: drops by 2.2 AP from 32.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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