AI Paper Atlas

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

Instance Adaptive Self-Training for Unsupervised Domain Adaptation

Ke Mei, Chuang Zhu, Jiaqi Zou, Shanghang Zhang

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 311 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 constant-threshold self-training after warm-up (ablation)adversarial warm-up model · GTA5 to CityscapesmIoU: 43.8 -> 45.1Improved
add instance adaptive selector (IAS) for pseudo-labels (ablation)constant-threshold self-training · GTA5 to CityscapesmIoU: 45.1 -> 49.8Improved
add confident-region KLD regularization (ablation)IAST with IAS · GTA5 to CityscapesmIoU: 49.8 -> 50.7Improved
add ignored-region entropy minimization (ablation)IAST with IAS and Rc · GTA5 to CityscapesmIoU: 50.7 -> 51.5Improved
add multi-scale testing (ablation)IAST · GTA5 to CityscapesmIoU: 51.5 -> 52.2Improved
use instance adaptive thresholds instead of class-balanced thresholds (ablation)IAS (alpha 0.2, beta 0.9) · GTA5 to CityscapesmIoU: 47.9 -> 50.5Improved
add EMA threshold momentum (beta 0 to 0.9) (ablation)IAS with alpha 0.2 · GTA5 to CityscapesmIoU: 49.8 -> 50.5Improved
raise EMA momentum beta from 0.9 to 0.99 (ablation)IAS with alpha 0.2 · GTA5 to CityscapesmIoU: 50.5 -> 50.0Hurt
raise pseudo-label proportion alpha from 0.2 to 0.5 (ablation)IAS with beta 0.9 · GTA5 to CityscapesmIoU: 50.5 -> 48.2Hurt
add hard-class weight decay (gamma 0 to 8) (ablation)IAS with alpha 0.2 · GTA5 to CityscapesmIoU: 50.5 -> 51.5Improved
increase gamma from 8 to 16 (ablation)IAST · GTA5 to CityscapesmIoU: 51.5 -> 50.9Hurt
increase lambda_c from 0.05 to 0.1 (with lambda_i 3.0) (ablation)IAST · GTA5 to CityscapesmIoU: 50.6 -> 51.5Improved

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