Papers › DMRNet++: Learning Discriminative Features with Decoupled Networks and Enriched Pairs...

DMRNet++: Learning Discriminative Features with Decoupled Networks and Enriched Pairs for One-Step Person Search

10 Nov 2022IEEE Transactions on Pattern Analysis and Machine Intelligence 2022 11archive 2025-07-28

Chuchu Han, Zhedong Zheng, Kai Su, Dongdong Yu, Zehuan Yuan, Changxin Gao, Nong Sang, Yi Yang

Person search aims at localizing and recognizing query persons from raw video frames, which is a combination of two sub-tasks, i.e., pedestrian detection and person re-identification. The dominant fashion is termed as the one-step person search that jointly optimizes detection and identification in a unified network, exhibiting higher efficiency. However, there remain major challenges: (i) conflicting objectives of multiple sub-tasks under the shared feature space, (ii) inconsistent memory bank caused by the limited batch size, (iii) underutilized unlabeled identities during the identification learning. To address these issues, we develop an enhanced decoupled and memory-reinforced network (DMRNet++). First, we simplify the standard tightly coupled pipelines and establish a task-decoupled framework (TDF). Second, we build a memory-reinforced mechanism (MRM), with a slow-moving average of the network to better encode the consistency of the memorized features. Third, considering the potential of unlabeled samples, we model the recognition process as semi-supervised learning. An unlabeled-aided contrastive loss (UCL) is developed to boost the identification feature learning by exploiting the aggregation of unlabeled identities. Experimentally, the proposed DMRNet++ obtains the mAP of 94.5% and 52.1% on CUHK-SYSU and PRW datasets, which exceeds most existing methods.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Pedestrian DetectionPerson Re-IdentificationPerson Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Search CUHK-SYSU DMRNet++ MAP 94.5 #9 of 16 Archive leaderboard report
Person Search CUHK-SYSU DMRNet++ Top-1 95.7 #9 of 16 Archive leaderboard report
Person Search PRW DMRNet++ Top-1 87.0 #4 of 15 Archive leaderboard report
Person Search PRW DMRNet++ mAP 52.1 #4 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections