AI Paper Atlas

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

Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation

Haoran Wang, Tong Shen, Wei Zhang, Ling-Yu Duan, Tao Mei

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 332 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 fine-grained adversarial training (ablation)DeepLab-v2 ResNet-101 · GTA5 -> CityscapesmIoU: 36.8 -> 46.9Improved
add self distillation (ablation)FADA · GTA5 -> CityscapesmIoU: 46.9 -> 49.2Improved
add multi-scale testing (ablation)FADA + self distillation · GTA5 -> CityscapesmIoU: 49.2 -> 50.1Improved
use soft labels instead of hard labels for class knowledge (ablation)FADA · GTA5 -> CityscapesmIoU: 45.7 -> 46.9Improved
use soft labels instead of hard labels for class knowledge (ablation)FADA · SYNTHIA -> CityscapesmIoU: 40.8 -> 41.5Improved
add confidence clipping (threshold 0.9) to soft labels (ablation)FADA · GTA5 -> CityscapesmIoU: 45.7 -> 46.9Improved
lower confidence clipping threshold from 0.9 to 0.7 (ablation)FADA · GTA5 -> CityscapesmIoU: 46.9 -> 46.2Hurt
add class-level fine-grained discriminator to a global feature alignment baseline (ablation)DeepLab-v2 ResNet-101 · GTA5 -> CityscapesmIoU: 39.4 -> 45.7Improved
add FADA adaptation to source-only VGG-16DeepLab-v2 VGG-16 · GTA5 -> CityscapesmIoU: 28.3 -> 43.8Improved

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