AI Paper Atlas

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

Weakly Supervised Training of Universal Visual Concepts for Multi-domain Semantic Segmentation

Petra Bevandić, Marin Oršić, Josip Šarić, Ivan Grubišić, Siniša Šegvić

IJCV 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 universal taxonomy with NLL+ instead of naive concatenation (ablation)SNp-RN18 · ADE20k val (joint Vistas-ADE20k training)mIoU: 36.8 -> 37.4Improved
add universal taxonomy with NLL+ instead of naive concatenation (ablation)SNp-RN18 · WildDash 2 minival (joint Vistas-WD2 training)mIoU: 55.3 -> 56.2Improved
add post-inference mapping to naive concatenation (ablation)SNp-RN18 · ADE20k val (joint Vistas-ADE20k training), VistasmIoU: 41.0 -> 42.2Improved
add post-inference mapping to naive concatenation (ablation)SNp-RN18 · Cityscapes val (joint Vistas-City training)mIoU: 76.8 -> 76.8No clear effect
train jointly on Vistas and ADE20k with NLL+ instead of single dataset (ablation)SNp-RN18 · Vistas val (joint Vistas-ADE20k training)mIoU: 46.4 -> 42.8Hurt
add NLL+ weak supervision instead of two-step pseudo-label training (ablation)SNp-RN18 · ADE20k val (joint Vistas-ADE20k training)mIoU: 34.1 -> 37.4Improved
add NLL+ instead of NLL-max (max over universal classes instead of sum) (ablation)SNp-RN18 · Cityscapes relabeled splitmIoU: 61.8 -> 74.3Improved
add NLL+ instead of naive concatenation (ablation)SNp-RN18 · Cityscapes relabeled splitmIoU: 67.6 -> 74.3Improved
add NLL+ instead of partial merge (ablation)SNp-RN18 · Cityscapes relabeled splitmIoU: 71.4 -> 74.3Improved
replace ResNet-18 pixel-level model by Mask2Former with universal taxonomy (ablation)NLL+ universal · Cross-dataset WD2mIoU: 43.9 -> 49.8Improved
add universal taxonomy instead of MSeg relabeling (ablation)SNp-DN161 · Vistas val (MSeg collection, default protocol)mIoU: 28.7 -> 44.2Improved
add universal taxonomy instead of MSeg relabeling (ablation)SNp-DN161 · Cityscapes val (MSeg collection, default protocol)mIoU: 77.0 -> 76.1Hurt

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