AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

MC-PanDA: Mask Confidence for Panoptic Domain Adaptation

Ivan Martinović, Josip Šarić, Siniša Šegvić

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 4 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 mask-wide loss scaling (MLS) to baseline consistency (ablation)MC-PanDA · Synthia->CityscapesPQ16: 39.6 -> 44.6Improved
Add confidence-based point filtering (CBPF) on top of MLS (ablation)MC-PanDA · Synthia->CityscapesPQ16: 44.6 -> 47.4Improved
Add mean-teacher consistency to supervised Synthia baseline (ablation)Mask2Former · Synthia->CityscapesPQ16: 30.8 -> 39.6Improved
Use mask-wide instead of image-wide loss scaling (ablation)MC-PanDA · Synthia->CityscapesPQ16: 42.1 -> 47.4Improved
Use all-masks teacher confidence instead of per-mask in CBPF (ablation)MC-PanDA · Synthia->CityscapesPQ16: 44.7 -> 47.4Improved
Use CBPF instead of random point sampling (ablation)MC-PanDA · Synthia->CityscapesPQ16: 44.2 -> 47.4Improved
Use tau1=0.99 instead of 0.968 for MLS with CBPF (ablation)MC-PanDA · Synthia->CityscapesPQ16: 47.2 -> 47.4No clear effect
Use stricter tau2=0.9 for point filtering (ablation)MC-PanDA · Synthia->VistasPQ16: 37.9 -> 38.7Improved
Set tau1 for stuff classes to 0.9 (ablation)MC-PanDA · Synthia->VistasPQ16: 38.7 -> 39.6Improved
Use MC-PanDA instead of EDAPS with the same MiT-B5 backboneMC-PanDA · Synthia->CityscapesPQ16: 41.2 -> 44.7Improved

Later papers that compared with this method

1 later accepted paper reports MC-PanDA as a baseline in their results tables; 1 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