Papers › Aggregating Deep Pyramidal Representations for Person Re-Idenfitication

Aggregating Deep Pyramidal Representations for Person Re-Idenfitication

20 Jun 2019International Conference on Computer Vision and Pattern Recognition Workshops (CVPR) 2019 6archive 2025-07-28

Niki Martinel, Gian Luca Foresti, Christian Micheloni

Learning discriminative, view-invariant and multi-scale representations of person appearance with different se- mantic levels is of paramount importance for person Re- Identification (Re-ID). A surge of effort has been spent by the community to learn deep Re-ID models capturing a holistic single semantic level feature representation. To improve the achieved results, additional visual attributes and body part-driven models have been considered. How- ever, these require extensive human annotation labor or de- mand additional computational efforts. We argue that a pyramid-inspired method capturing multi-scale information may overcome such requirements. Precisely, multi-scale stripes that represent visual information of a person can be used by a novel architecture factorizing them into latent discriminative factors at multiple semantic levels. A multi- task loss is combined with a curriculum learning strategy to learn a discriminative and invariant person representation which is exploited for triplet-similarity learning. Results on three benchmark Re-ID datasets demonstrate that better performance than existing methods are achieved (e.g., more than 90% accuracy on the Duke-MTMC dataset).

PaperPDFCode

Code

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.

Code Syntology ran Syntology

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

Tasks

Person Re-Identification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification DukeMTMC-reID PyrNet (+ReRank) Rank-1 90.3 #18 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID PyrNet (+ReRank) mAP 87.7 #18 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID PyrNet Rank-1 87.1 #60 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID PyrNet mAP 74.0 #60 of 94 Archive leaderboard report
Person Re-Identification Market-1501 PyrNet (multi-shot+ReRank) Rank-1 96.1 #27 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PyrNet (multi-shot+ReRank) mAP 94.0 #27 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PyrNet (multi-shot) Rank-1 95.2 #68 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PyrNet (multi-shot) mAP 86.7 #68 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PyrNet (single-shot+ReRank) Rank-1 94.6 #77 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PyrNet (single-shot+ReRank) mAP 91.4 #77 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PyrNet (single-shot) Rank-1 93.6 #85 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PyrNet (single-shot) mAP 81.7 #85 of 135 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