AI Paper Atlas

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

An Empirical Study on Multi-domain Robust Semantic Segmentation

Yajie Liu, Pu Ge, Qingjie Liu, Shichao Fan, Yunhong Wang

IJCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive 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 DomainMix (ablation)Segformer-MiT-B5 · RVC six datasetsh.mean mIoU: 64.07 -> 64.51Improved
add CutMix (ablation)Segformer-MiT-B5 · RVC six datasetsh.mean mIoU: 64.07 -> 64.54Improved
add Copy-Paste (ablation)Segformer-MiT-B5 · RVC six datasetsh.mean mIoU: 64.07 -> 64.19No clear effect
combine Copy-Paste and DomainMix (ablation)Segformer-MiT-B5 · RVC six datasetsh.mean mIoU: 64.07 -> 64.82Improved
add CutMix on top of Copy-Paste and DomainMix (ablation)Segformer-MiT-B5 · RVC six datasetsh.mean mIoU: 64.82 -> 64.50Hurt
add class-balanced sampling (ablation)Segformer-MiT-B5 · RVC six datasetsh.mean mIoU: 64.1 -> 64.2No clear effect
add warmup (ablation)Segformer-MiT-B5 · RVC six datasetsh.mean mIoU: 64.1 -> 64.2No clear effect
combine class-balanced sampling and warmup (ablation)Segformer-MiT-B5 · RVC six datasetsh.mean mIoU: 64.1 -> 64.8Improved
add domain generalization method IRM (ablation)DeepLabv3+/ResNet50 · RVC six datasetsh.mean mIoU: 49.6 -> 37.7Hurt
add domain generalization method DANN (ablation)DeepLabv3+/ResNet50 · RVC six datasetsh.mean mIoU: 49.6 -> 48.1Hurt
train on six datasets instead of CityScapes alone (ablation)Segformer-MiT-B1 · CityScapesmIoU: 72.0 -> 70.4Hurt
train on six datasets instead of CityScapes alone (ablation)Segformer-MiT-B5 · CityScapesmIoU: 76.9 -> 76.4No clear effect

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