AI Paper Atlas

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

Generalize Then Adapt: Source-Free Domain Adaptive Semantic Segmentation

Jogendra Nath Kundu, Akshay Kulkarni, Amit Singh, Varun Jampani, R. Venkatesh Babu

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 114 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 multi-source ERM training on augmentation groups (ablation)single-source self-training baseline · GTA5->Cityscapes (DeepLabv2 R101)mIoU: 44.4 -> 47.6Improved
replace ERM with Domain-experts++ (DE++) heads (ablation)vendor-side model · GTA5->Cityscapes (DeepLabv2 R101)mIoU: 47.6 -> 48.0Improved
replace DE++ with Leave-one-out++ (LO++) heads (ablation)vendor-side model · GTA5->Cityscapes (DeepLabv2 R101)mIoU: 48.0 -> 51.6Improved
add cPAE for pseudo-label extraction (ablation)client-side self-training · GTA5->Cityscapes (DeepLabv2 R101)mIoU: 51.6 -> 53.4Improved
add cPAE at inference (without cPAE pseudo-labels) (ablation)client-side self-training · GTA5->Cityscapes (DeepLabv2 R101)mIoU: 51.6 -> 52.5Improved
add cPAE at inference (with cPAE pseudo-labels) (ablation)client-side self-training · GTA5->Cityscapes (DeepLabv2 R101)mIoU: 53.4 -> 54.2Improved
add cPAE (pseudo-labels) on VGG-16 (ablation)source-free adaptation · GTA5->Cityscapes (FCN8s VGG-16)mIoU: 43.4 -> 45.9Improved
add cPAE (pseudo-labels) on SYNTHIA (ablation)source-free adaptation · SYNTHIA->Cityscapes (16 classes, ResNet-101)mIoU: 48.1 -> 52.0Improved
add cPAE (pseudo-labels) on SYNTHIA VGG-16 (ablation)source-free adaptation · SYNTHIA->Cityscapes (16 classes, VGG-16)mIoU: 40.0 -> 41.3Improved
use LO++ instead of ERM for source-only training (ablation)vendor-side model · GTA5->Cityscapes domain generalization (ResNet-101)mIoU: 43.1 -> 43.5Improved
use LO++ instead of ERM for source-only training (ablation)vendor-side model · SYNTHIA->Cityscapes domain generalization (VGG16)mIoU: 36.9 -> 37.4Improved
use the proposed augmentation groups with prior self-training method IASTIAST · GTA5->Cityscapes (DeepLabv2 R101)mIoU: 52.2 -> 52.8Improved

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