AI Paper Atlas

Research map / Detection and segmentation / CNN features

Deep Watershed Transform for Instance Segmentation

Min Bai, Raquel Urtasun

CVPR 2017 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 560 citations (OpenAlex)

Check 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 PSPNet rather than LRR for semantic segmentation input (ablation)Deep Watershed Transform · Cityscapes val setAP: 20.2% -> 21.2%Improved
use semantic-segmentation confidence ordering for bus, truck, and train rather than random ordering (ablation)Deep Watershed Transform · Cityscapes val setAverage AP: 20.50% -> 21.24%Improved
use oracle IoU ordering rather than random ordering (ablation)Deep Watershed Transform · Cityscapes val setAverage AP: 20.50% -> 27.58%Improved
use oracle IoU ordering rather than semantic-confidence ordering (ablation)Deep Watershed Transform · Cityscapes val setAverage AP: 21.24% -> 27.58%Improved

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