AI Paper Atlas

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

Exploiting Diverse Characteristics and Adversarial Ambivalence for Domain Adaptive Segmentation

Bowen Cai, Huan Fu, Rongfei Jia, Binqiang Zhao, Hua Li, Yinghui Xu

AAAI 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 3 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
Apply DCAA instead of the strongest listed baselineGTA5 → Cityscapes* adaptation · Cityscapes*mIoU: 45.4 -> 51.4Improved
Apply DCAA instead of the strongest listed baselineSYNTHIA → Cityscapes* adaptation · Cityscapes*mIoU: 42.5 -> 47.4Improved
Use DCAA rather than OCDA++GTA5 → BDD100K · BDD100K Avg.mIoU: 25.7 -> 34.7Improved
Replace Mix-Head, Sep-Head, or SM-Head with CAM (ablation)DCAA · GTA5 → Cityscapes*mIoU (Stage 1): 46.0 -> 47.2; 45.3 -> 47.2; 45.6 -> 47.2Improved
Replace CAM with Sep-Head or SM-Head (ablation)DCAA · GTA5 → Cityscapes*mIoU (Stage 1): 47.2 -> 45.3; 47.2 -> 45.6Hurt
Use progressive condition-specific adversarial training rather than standard adversarial training (ablation)DCAA · GTA5 → Cityscapes*mIoU: 47.8 -> 51.4Improved
Use attentive pseudo-label assignment rather than simple voting (ablation)DCAA-S1 · GTA5 → Cityscapes*mIoU: 48.7 -> 49.8Improved
Weight target pseudo-label cross-entropy with discriminator confidence (ablation)DCAA self-training with λp = 0.6 · GTA5 → Cityscapes*mIoU: 48.3 -> 50.6Improved
Add adversarial loss for hard adaptation regions (ablation)DCAA self-training with λp = 0.6 · GTA5 → Cityscapes*mIoU: 50.6 -> 51.4Improved
Use condition-guided style transfer instead of CycleGAN (ablation)Mix-Head adaptation model · GTA5 → Cityscapes*mIoU (Stage 1): 42.7 -> 46.0Improved
Use MUNIT instead of CycleGAN for translation (ablation)Mix-Head adaptation model · GTA5 → Cityscapes*mIoU (Stage 1): 42.7 -> 43.4Improved
Replace CGST with MUNIT or StarGAN translation (ablation)DCAA Stage 2 · GTA5 → Cityscapes*mIoU: 45.6 -> 51.4; 48.3 -> 51.4Hurt

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