AI Paper Atlas

Research map / Benchmarks / CUHK03 labeled

CUHK03 labeled leaderboard

21 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CUHK03 labeled. Best Rank-1: 90.39 (HAP2S P, ECCV 2018).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CUHK03 labeled · Rank-1

21 papers, each with its best reported number for its own method; higher is better.

#Rank-1 ↑MethodPaperTopic
190.39HAP2S P
ResNet-50 (pre-trained)
Hard-Aware Point-to-Set Deep Metric for Person Re-identification
ECCV 2018 · Table 1
Recognition and long-tail
288.7PDCPose-Driven Deep Convolutional Model for Person Re-Identification
ICCV 2017 · Table 4
Recognition and long-tail
387.57QI-IRA(2,1)QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification
AAAI 2024 · Table 1
Recognition and long-tail
486.8SCSN (4 stages)
ResNet50
Salience-Guided Cascaded Suppression Network for Person Re-Identification
CVPR 2020 · Table 3
Recognition and long-tail
585.4Part-aligned (ours)
GoogLeNet
Deeply-Learned Part-Aligned Representations for Person Re-Identification
ICCV 2017 · Table (CUHK03 labeled)
Recognition and long-tail
681.1RGA-SC
ResNet-50
Relation-Aware Global Attention for Person Re-Identification
CVPR 2020 · State-of-the-art comparison ta
Recognition and long-tail
780.7UMTS (ResNet-50)
ResNet-50
Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
AAAI 2020 · Table: person re-id comparison
CNN features
880.6Ours
ResNet50
Coarse-To-Fine Person Re-Identification With Auxiliary-Domain Classification and Second-Order Information Bottleneck
CVPR 2021 · Table 4
Recognition and long-tail
980.1SAN
ResNet-50
Semantics-Aligned Representation Learning for Person Re-Identification
AAAI 2020 · State-of-the-art comparison ta
Recognition and long-tail
1080IS-GAN_DC
ResNet-50
Disentangled Representations for Short-Term and Long-Term Person Re-Identification
TPAMI 2021 · text
Recognition and long-tail
11 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

CUHK03 labeled · mAP

14 papers, each with its best reported number for its own method; higher is better.

#mAP ↑MethodPaperTopic
187.26QI-IRA(2,1)QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification
AAAI 2024 · Table 1
Recognition and long-tail
284SCSN (4 stages)
ResNet50
Salience-Guided Cascaded Suppression Network for Person Re-Identification
CVPR 2020 · Table 3
Recognition and long-tail
379.3Ours
ResNet50
Coarse-To-Fine Person Re-Identification With Auxiliary-Domain Classification and Second-Order Information Bottleneck
CVPR 2021 · Table 4
Recognition and long-tail
477.4RGA-SC
ResNet-50
Relation-Aware Global Attention for Person Re-Identification
CVPR 2020 · State-of-the-art comparison ta
Recognition and long-tail
577.3IS-GAN_DC
ResNet-50
Disentangled Representations for Short-Term and Long-Term Person Re-Identification
TPAMI 2021 · text
Recognition and long-tail
676.4SAN
ResNet-50
Semantics-Aligned Representation Learning for Person Re-Identification
AAAI 2020 · State-of-the-art comparison ta
Recognition and long-tail
776.1BAT-net w/ AiABilinear Attention Networks for Person Retrieval
ICCV 2019 · Table 1
Attention and transformers
875.6Ours-F
ResNet-50
Relation Network for Person Re-Identification
AAAI 2020 · Table 1
Recognition and long-tail
975.5UMTS (ResNet-50)
ResNet-50
Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
AAAI 2020 · Table: person re-id comparison
CNN features
1073.6P2-Net (+ triplet loss)
ResNet-50
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
ICCV 2019 · Table 6
Recognition and long-tail
4 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.