AI Paper Atlas

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

Bipartite Mode Matching for Vision Training Set Search from a Hierarchical Data Server

Yue Yao, Ruining Yang, Tom Gedeon

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 3 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
use balanced K-means instead of standard K-means for source clustering (ablation)BMM · AlicePerson re-ID (5% IDs)mAP (%): 26.08 -> 28.16Improved
replace greedy direct matching (with duplicates) by Hungarian one-to-one matching (ablation)BMM · AlicePerson re-ID (5% IDs)mAP (%): 20.14 -> 26.08Improved
replace direct matching with duplicates deleted by Hungarian matching (ablation)BMM · AlicePerson re-ID (5% IDs)mAP (%): 22.07 -> 26.08Improved
add hierarchical clustering of the data server alone, keeping greedy search (ablation)BMM baseline · AlicePerson re-IDmAPNo clear effect
add bipartite mode matching alone, keeping flat clustering (ablation)BMM baseline · AlicePerson re-IDmAPNo clear effect
combine hierarchical server with bipartite matching (ablation)BMM baseline · AlicePerson re-IDmAPImproved
use hierarchical instead of flat clustering on source server (ablation)BMM · Cluster-number analysis (Fig. 4)FID and mAPImproved
searched training set with BMM instead of random sampling at 5% IDsIDE on AlicePerson · AlicePerson re-ID (5% IDs)mAP (%): 14.49 -> 26.08Improved
BMM instead of SnP on ExDark detectionRetinaNet · ExDark vehicle detection (5% images)mAP (%): 32.15 -> 34.83Improved
add MMT pseudo-labeling to the searched training setBMM · Market re-IDmAP (%): 26.08% -> 78.95%Improved
BMM + MMT instead of greedy search + MMTMMT · Market re-IDmAP (%): 76.98 -> 78.95Improved
increase number of source and target clusters beyond small values (ablation)BMM · Cluster-number analysisFID and mAP: FID 9.8, mAP 83.0% at L = 20Improved

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