AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Cross-View Regularization for Domain Adaptive Panoptic Segmentation

CVPR 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive segmentation · 48 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 multi-task self-training to source-only training (ablation)PSN · SYNTHIA → CityscapesmPQ: 21.8 -> 24.8Helped
add inter-task regularization to MTST (ablation)CVRN · SYNTHIA → CityscapesmPQ: 24.8 -> 28.0Helped
add inter-style regularization to MTST (ablation)CVRN · SYNTHIA → CityscapesmPQ: 24.8 -> 28.9Helped
combine inter-task and inter-style regularization (ablation)MTST · SYNTHIA → CityscapesmPQ: 28.9 -> 32.1Helped
apply cross-view regularizationdomain-adaptive panoptic segmentation · SYNTHIA → CityscapesmPQ: 26.6 -> 30.9; +3.3Helped
apply cross-view regularizationdomain-adaptive panoptic segmentation · SYNTHIA → CityscapesmPQ: 28.1 -> 32.0; +3.9Helped
apply cross-view regularizationdomain-adaptive panoptic segmentation · SYNTHIA → CityscapesmPQ: 27.1 -> 32.4; +5.3Helped

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