AI Paper Atlas

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

Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labels

Venkanna Babu Guthula, Oswin Krause, Dimitri Gominski, Hui Zhang, Johan Mottelson, Ankit Kariryaa, Nico Lang, Christian Igel

ECCV 2026 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 0 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 consistency loss L_Con (ablation)AnS (L_CE) · Las Vegas, random misalignmentIoU_seg: 0.71 -> 0.74Improved
Add consistency loss L_Con (ablation)AnS (L_CE) · Las Vegas, systematic misalignmentIoU_seg: 0.39 -> 0.41Improved
Add geometric augmentation alone (ablation)AnS (L_CE) · Las Vegas, random misalignmentIoU_seg: 0.71 -> 0.66Hurt
Add geometric augmentation alone (ablation)AnS (L_CE) · Las Vegas, systematic misalignmentIoU_seg: 0.39 -> 0.72Improved
Add both L_Con and augmentation (ablation)AnS (L_CE) · Las Vegas, systematic misalignmentIoU_align: 0.41 -> 0.88Improved
Add both L_Con and augmentation (ablation)AnS (L_CE) · Las Vegas, random misalignmentIoU_seg: 0.71 -> 0.79Improved
Train TNet and SNet end-to-end instead of two-stage with frozen pretrained TNet (ablation)AnS · ReBO testIoU_seg: 0.38 -> 0.62Improved
Freeze pretrained SNet encoder instead of fine-tuning (ablation)AnS SNet (ConvNeXt DINOv3) · systematic misalignment (Las Vegas)IoU_seg: 0.41 -> 0.69Improved
Use AnS instead of unsupervised baselines (MA, AC, SC)AnS · Las Vegas, systematic misalignmentIoU_align: MA 0.47, AC 0.46 -> AnS 0.88Improved
Use AnS instead of supervised MapRepairAnS · Paris, random misalignmentIoU_align: MR 0.57 -> AnS 0.67 (random); MR 0.68 -> AnS 0.65 (systematic)Mixed

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