Papers › Interpretable and Generalizable Person Re-Identification with Query-Adaptive...

Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting

23 Apr 2019ECCV 2020 8arXiv:1904.10424archive 2025-07-28

Shengcai Liao, Ling Shao

For person re-identification, existing deep networks often focus on representation learning. However, without transfer learning, the learned model is fixed as is, which is not adaptable for handling various unseen scenarios. In this paper, beyond representation learning, we consider how to formulate person image matching directly in deep feature maps. We treat image matching as finding local correspondences in feature maps, and construct query-adaptive convolution kernels on the fly to achieve local matching. In this way, the matching process and results are interpretable, and this explicit matching is more generalizable than representation features to unseen scenarios, such as unknown misalignments, pose or viewpoint changes. To facilitate end-to-end training of this architecture, we further build a class memory module to cache feature maps of the most recent samples of each class, so as to compute image matching losses for metric learning. Through direct cross-dataset evaluation, the proposed Query-Adaptive Convolution (QAConv) method gains large improvements over popular learning methods (about 10%+ mAP), and achieves comparable results to many transfer learning methods. Besides, a model-free temporal cooccurrence based score weighting method called TLift is proposed, which improves the performance to a further extent, achieving state-of-the-art results in cross-dataset person re-identification. Code is available at https://github.com/ShengcaiLiao/QAConv.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

shengcailiao/QAConv officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TransMatcher: Deep Image Matching Through Transformers for Generalizable Person... (arXiv:2105.14432; that paper's own run record: 13 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Domain GeneralizationGeneralizable Person Re-identificationMetric LearningPerson Re-IdentificationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Generalizable Person Re-identification CUHK03-NP (detected) QAConv MSMT17-All->Rank-1 25.3 #5 of 5 Archive leaderboard report
Generalizable Person Re-identification CUHK03-NP (detected) QAConv MSMT17-All->mAP 22.6 #5 of 5 Archive leaderboard report
Generalizable Person Re-identification CUHK03-NP (detected) QAConv Market-1501->Rank-1 9.9 #5 of 5 Archive leaderboard report
Generalizable Person Re-identification CUHK03-NP (detected) QAConv Market-1501->mAP 8.6 #5 of 5 Archive leaderboard report
Generalizable Person Re-identification DukeMTMC-reID QAConv MSMT17->Rank1 69.4 #3 of 4 Archive leaderboard report
Generalizable Person Re-identification DukeMTMC-reID QAConv MSMT17->mAP 52.6 #3 of 4 Archive leaderboard report
Generalizable Person Re-identification MSMT17 QAConv Market-1501->Rank1 22.6 #4 of 4 Archive leaderboard report
Generalizable Person Re-identification MSMT17 QAConv Market-1501->mAP 7.0 #4 of 4 Archive leaderboard report
Generalizable Person Re-identification Market-1501 QAConv MSMT17-All->Rank-1 72.6 #5 of 5 Archive leaderboard report
Generalizable Person Re-identification Market-1501 QAConv MSMT17-All->mAP 43.1 #5 of 5 Archive leaderboard report
Unsupervised Domain Adaptation CUHK03 to Market QAConv R1 85.0 #5 of 9 Archive leaderboard report
Unsupervised Domain Adaptation CUHK03 to Market QAConv R10 - #5 of 9 Archive leaderboard report
Unsupervised Domain Adaptation CUHK03 to Market QAConv R5 - #5 of 9 Archive leaderboard report
Unsupervised Domain Adaptation CUHK03 to Market QAConv mAP 66.5 #5 of 9 Archive leaderboard report
Unsupervised Domain Adaptation Market to CUHK03 QAConv R1 33.3 #5 of 8 Archive leaderboard report
Unsupervised Domain Adaptation Market to CUHK03 QAConv R10 - #5 of 8 Archive leaderboard report
Unsupervised Domain Adaptation Market to CUHK03 QAConv R5 - #5 of 8 Archive leaderboard report
Unsupervised Domain Adaptation Market to CUHK03 QAConv mAP 32.9 #5 of 8 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.

Methods

Convolution

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