AI Paper Atlas

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

Prior to Segment: Foreground Cues for Weakly Annotated Classes in Partially Supervised Instance Segmentation

David Biertimpel, Sindi Shkodrani, Anil S. Baslamisli, Nóra Baka

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 16 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 object mask prior (OMP) from box-head CAMs to the Mask R-CNN class-agnostic mask headOur Mask R-CNN (R-50-FPN) · non-voc -> vocAP: 26.4 -> 36.5Improved
add object mask prior (OMP) from box-head CAMs to the Mask R-CNN class-agnostic mask headOur Mask R-CNN (R-50-FPN) · voc -> non-vocAP: 18.9 -> 31.9Improved
add OMPOur Mask R-CNN (R-101-FPN) · voc -> non-vocAP: 21.0 -> 33.2Improved
add OMPOur Mask R-CNN (R-101-FPN) · non-voc -> vocAP: 27.7 -> 37.1Improved
add OMP, evaluated on ambiguous RoIsOur Mask R-CNN (R-50-FPN) · voc -> non-voc ambiguous instancesAP: 6.5 -> 17.1Improved
add OMP, evaluated on non-ambiguous RoIsOur Mask R-CNN (R-50-FPN) · Full COCO non-ambiguous instancesAP: 36.2 -> 38.0Improved
add OMP under full mask supervision on all COCO classesOur Mask R-CNN · COCO (fully supervised)AP: +1.6 APImproved
let mask gradients backpropagate into box head CAMs (OMP vs plain CAM of Mask R-CNN) (ablation)OPMask · COCO CAM mask AP (train all, test all)AP: 0.2 -> 8.8Improved
replace Mask R-CNN with OPMask CAM training on voc classes only, test on non-voc (ablation)OPMask · COCO CAM mask AP (train voc, test non-voc)AP: 0.2 -> 3.3Improved
OPMask versus CPMask with a ResNet-101 backboneOPMask · voc -> non-vocAP: 34.0 vs 33.2No clear effect
OPMask versus ShapeProp with ResNet-50OPMask · voc -> non-vocAP: 30.4 -> 31.9Improved

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