AI Paper Atlas

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

CIA: Cluster-Instance Alignment for Unsupervised Day-Night Vehicle Re-Identification

Yongguo Ling, Chen Zhang, Yiming Liu, Wenhao Shao

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 1 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 DGM cluster-level matching to the baseline (ablation)Base (ADCA-style dual-stream) · DN-348 Day-to-NightRank-1 (%): 63.17 -> 65.32Improved
add MAA instance-level alignment to the baseline (ablation)Base (ADCA-style dual-stream) · DN-348 Day-to-NightRank-1 (%): 63.17 -> 63.76Improved
add MAA to the baseline (ablation)Base · DN-348 Night-to-DayRank-1 (%): 76.61 -> 78.22Improved
combine DGM and MAA (ablation)Base · DN-348 Day-to-NightRank-1 (%): 65.32 -> 67.74Improved
replace PGM cluster matching with DGM (ablation)Base · DN-348 Night-to-DayRank-1 (%): 77.52 -> 79.33Improved
replace MMD with MAA (ablation)ADCA · DN-348 Day-to-NightRank-1 (%): 63.22 -> 64.32Improved
replace MarginMMD with MAA (ablation)ADCA · DN-348 Night-to-DayRank-1 (%): 78.75 -> 78.88No clear effect
use continuous similarity-based dictionary scores instead of discrete scores (ablation)DGM · DN-348Rank-1 (%): Day-to-Night 66.96 -> 67.74; Night-to-Day 80.36 -> 79.86Mixed
use continuous instead of fixed dictionary scores (ablation)DGM · DN-348 Day-to-NightRank-1 (%): 66.92 -> 67.74Improved
apply CIA to pedestrian RegDB visible-thermalBase · RegDB Visible-to-ThermalRank-1 (%): 67.20 -> 86.12Improved
CIA vs best prior method on DN-Wild day-to-nightCIA · DN-Wild Day-to-NightRank-1 (%): 48.63 -> 49.12Improved

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