AI Paper Atlas

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

Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

Zhengkai Jiang, Yuxi Li, Ceyuan Yang, Peng Gao, Yabiao Wang, Ying Tai, Chengjie Wang

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 147 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 prototypical contrast adaptation (feature+output) (ablation)source-only DeepLab-v2 · GTA5->CityscapesmIoU: 37.3 -> 48.8Improved
add ProCA before self-training (ablation)adaptive self-training · GTA5->CityscapesmIoU: 43.9 -> 55.1Improved
add class-wise adaptive threshold self-training (ablation)ProCA · GTA5->CityscapesmIoU: 48.8 -> 55.1Improved
add multi-scale testing (ablation)ProCA + adaptive ST · GTA5->CityscapesmIoU: 55.1 -> 56.3Improved
add output-level to feature-level adaptation (multi-level) (ablation)ProCA · GTA5->CityscapesmIoU: 47.9 -> 48.8Improved
use ProCA instead of FADA (ablation)source-only · GTA5->CityscapesmIoU: 46.9 -> 48.8Improved
use ProCA instead of pixel memory bank (ablation)source-only · GTA5->CityscapesmIoU: 47.6 -> 48.8Improved
use mixed source-target prototype updating instead of fixed prototypes (ablation)ProCA · GTA5->CityscapesmIoU: 47.8 -> 48.8Improved
add cross-domain t->s contrast to source-source contrast (ablation)ProCA · GTA5->CityscapesmIoU: 44.9 -> 48.8Improved
use adaptive class-wise thresholds instead of naive 0.9 threshold (ablation)ProCA self-training · GTA5->CityscapesmIoU: 55.2 -> 56.3Improved
use ProDA prototype-based pseudo labels instead of adaptive thresholds (ablation)ProCA self-training · GTA5->CityscapesmIoU: 56.3 -> 57.5Improved
raise pseudo-label percentage eta from 60 to 90 (ablation)ProCA self-training · GTA5->CityscapesmIoU: 55.1 -> 52.5Hurt

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