AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

ProMerge: Prompt and Merge for Unsupervised Instance Segmentation

Dylan J Li, Gyungin Shin

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 6 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 background-based mask pruning to prompt-and-merge (ablation)ProMerge · COCO2017mask AP: 0.4 -> 2.1Improved
add connected-component splitting (ablation)ProMerge · COCO2017mask AR: 4.7 -> 7.5Improved
add merging to prompting without pruning (ablation)ProMerge · COCO2017mask AP: 0.5 -> 0.4Hurt
add pixel-wise voting for background aggregation (ablation)ProMerge · COCO2017mask AP: 1.2 -> 2.4Improved
use Cascade filtering instead of IoA or feature-similarity filtering (ablation)ProMerge · COCO2017mask AP: 1.7 / 2.0 -> 2.4Improved
use both feature similarity and IoA merging conditions (ablation)ProMerge · COCO2017mask AP: 2.2 -> 2.4Improved
train detector on ProMerge pseudo-labels instead of MaskCut pseudo-labelsCascade Mask R-CNN · Average over 6 benchmarksAP: 7.0 -> 7.9Improved
replace normalized-cut with prompt-and-mergeunsupervised instance segmentation · COCO2017speed: 0.54 FPS, about 1.6x TokenCut and 3.6x MaskCutImproved
increase stride beyond 4 to 15 or 30ProMerge · COCO2017AP/ARHurt

Later papers that compared with this method

3 later accepted papers report ProMerge as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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