AI Paper Atlas

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

UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions

Siyuan Yao, Rui Zhu, Ziqi Wang, Wenqi Ren, Yanyang Yan, Xiaochun Cao

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 14 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 controllable scenario generator (CSG) data (ablation)baseline tracker · NAT2021 (ablation)AUC: 49.11 -> 50.90Improved
add domain-customized adapter (DCA) (ablation)baseline tracker · NAT2021 (ablation)AUC: 49.11 -> 50.56Improved
add TCA to CSG (ablation)UMDATrack · NAT2021AUC: 50.90 -> 52.27Improved
add DCA to CSG+TCA (ablation)UMDATrack · NAT2021AUC: 52.27 -> 54.58Improved
add TCA to CSG+DCA (ablation)UMDATrack · NAT2021precision: 67.49 -> 70.78Improved
update EMA each epoch instead of every 5 epochs (ablation)UMDATrack · NAT2021AUC: 52.90 -> 54.48Improved
update EMA each epoch instead of each batch (ablation)UMDATrack · NAT2021AUC: 53.89 -> 54.48Improved
raise synthetic dataset sampling ratio from 1 to 4 (ablation)UMDATrack · NAT2021AUC: 53.13 -> 54.58Improved
raise synthetic dataset sampling ratio from 4 to 6 (ablation)UMDATrack · NAT2021AUC: 54.58 -> 54.26No clear effect
add text prompts to CSG (ablation)CSG generator · NAT2021AUC: 52.53 -> 54.58Improved
use CSG instead of CycleGAN (ablation)data generator · NAT2021AUC: 51.10 -> 54.58Improved
use CSG instead of UNIT (ablation)data generator · NAT2021AUC: 50.23 -> 54.58Improved

Later papers that compared with this method

1 later accepted paper reports UMDATrack as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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