AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detection

Hyewon Park, Hyejin Park, Jueun Ko, Dongbo Min

ICCV 2025 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 5 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 MIMA to full tuning (ablation)Full Tuning · Cityscapes-to-ACDC (10 rounds)mean mIoU: 59.3 -> 61.9Improved
add DDSD to full tuning (ablation)Full Tuning · Cityscapes-to-ACDC (10 rounds)mean mIoU: 59.3 -> 59.8Improved
add DDSD to full tuning (ablation)Full Tuning · Cityscapes-to-ACDC (10 rounds)FPS: 1.976 -> 2.546Improved
add DDSD and MIMA together (ablation)Full Tuning · Cityscapes-to-ACDC (10 rounds)mean mIoU: 59.3 -> 62.2Improved
add DDSD on top of FT+MIMA over 20 rounds (ablation)FT+MIMA · Cityscapes-to-ACDC (20 rounds)mean mIoU: 59.6 -> 61.5Improved
add DDSD to full tuning over 20 rounds (ablation)Full Tuning · Cityscapes-to-ACDC (20 rounds)mean mIoU: 55.9 -> 58.9Improved
add reconstruction loss weight 0.3 vs none (ablation)FT+MIMA · Cityscapes-to-ACDC (10 rounds)mIoU: 61.3 -> 61.9Improved
raise reconstruction loss weight to 1.0 (ablation)FT+MIMA · Cityscapes-to-ACDC (10 rounds)mIoU: 61.9 -> 60.6Hurt
use dynamic DDSD detector instead of fixed-threshold ADD (ablation)Hybrid-TTA · OnDA rain benchmarkmean mIoU: 64.7 -> 66.73Improved
always use FT instead of DDSD switching (with MIMA) (ablation)Hybrid-TTA · Cityscapes-to-ACDC (10 rounds)mean mIoU: 62.2 -> 61.9Hurt
use only adapter tuning (with MIMA) (ablation)Hybrid-TTA · Cityscapes-to-ACDC (10 rounds)mean mIoU: 62.2 -> 59.27Hurt
add MIMA to adapter tuning (ablation)Adapter Tuning · OnDA rain benchmark (target mean)mIoU: 60.5 -> 65.3Improved

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