Person Re Identification On Dukemtmc Reid
評価指標
Rank-1
mAP
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Rank-1 | mAP |
|---|---|---|
| auto-reid-searching-for-a-part-aware-convnet | 91.4 | 89.2 |
| on-the-unreasonable-effectiveness-of-1 | 95.6 | 96.1 |
| unsupervised-person-re-identification-by-soft | 79.8 | 48 |
| random-erasing-data-augmentation | 73.0 | 56.6 |
| improving-person-re-identification-by | 70.69 | 51.88 |
| improved-person-re-identification-based-on | 81.8 | 68.6 |
| joint-detection-and-identification-feature | 68.1 | 47.4 |
| deep-attention-aware-feature-learning-for | 87.9 | 77.9 |
| adaptivereid-adaptive-l2-regularization-in | 92.2 | 90.7 |
| flipreid-closing-the-gap-between-training-and | 93.0 | 90.7 |
| top-db-net-top-dropblock-for-activation | 90.9 | 88.6 |
| identity-guided-human-semantic-parsing-for | 89.6 | 80 |
| a-coarse-to-fine-pyramidal-model-for-person | 89.0 | 79.0 |
| deep-attention-aware-feature-learning-for | 91.7 | 89.6 |
| unlabeled-samples-generated-by-gan-improve | 67.68 | 47.13 |
| joint-discriminative-and-generative-learning | 90.26 | 88.31 |
| incremental-learning-in-person-re | 80.0 | 60.2 |
| relation-preserving-triplet-mining-for | 93.5 | 89.2 |
| learning-to-disentangle-scenes-for-person-re | 92.91 | 91.0 |
| deep-miner-a-deep-and-multi-branch-network | 91.20 | 81.80 |
| top-db-net-top-dropblock-for-activation | 87.5 | 73.5 |
| unsupervised-person-re-identification | 30.4 | 16.4 |
| disassembling-the-dataset-a-camera-alignment | 82.5 | 67.3 |
| clip-reid-exploiting-vision-language-model | 90.8 | 83.1 |
| template-aware-transformer-for-person | 91.5 | 82.5 |
| person-re-identification-past-present-and | 65.22 | 44.99 |
| resource-aware-person-re-identification | 84.4 | 80.0 |
| improved-person-re-identification-based-on | 86.4 | 83.7 |
| unsupervised-pre-training-for-person-re | 93.99 | 92.77 |
| abd-net-attentive-but-diverse-person-re | 89.0 | 78.59 |
| person-re-identification-in-the-3d-space | 76.66 | 57.89 |
| camera-aware-proxies-for-unsupervised-person | 87.7 | 76 |
| graph-based-person-signature-for-person-re | 88.2 | 78.7 |
| viewpoint-aware-loss-with-angular | 93.9 | 91.8 |
| parameter-free-spatial-attention-network-for | 89.0 | 85.9 |
| transreid-transformer-based-object-re | 91.1 | 82.1 |
| in-defense-of-the-triplet-loss-for-person-re | 72.44 | 53.50 |
| pedestrian-alignment-network-for-large-scale | 71.59 | 51.51 |
| omni-scale-feature-learning-for-person-re | 88.6 | 73.5 |
| camera-style-adaptation-for-person-re | 78.32 | 57.61 |
| deep-constrained-dominant-sets-for-person-re | 88.5 | 86.1 |
| body-part-based-representation-learning-for | 93.9 | 92.9 |
| aggregating-deep-pyramidal-representations | 90.3 | 87.7 |
| beyond-part-models-person-retrieval-with | 81.8 | 66.1 |
| learning-discriminative-features-with | 88.7 | 78.4 |
| bags-of-tricks-and-a-strong-baseline-for-deep | 90.2 | 89.1 |
| learning-diverse-features-with-part-level | 91.6 | 81.2 |
| shufflenet-an-extremely-efficient | - | 48.09 |
| person-re-identification-by-local-maximal | 30.75 | 17.04 |
| counterfactual-attention-learning-for-fine | 90 | 80.5 |
| aggregating-deep-pyramidal-representations | 87.1 | 74.0 |
| unsupervised-pre-training-for-person-re | 91.9 | 84.1 |
| plip-language-image-pre-training-for-person | - | 81.7 |
| attention-network-robustification-for-person | 88.8 | 78.9 |
| disassembling-the-dataset-a-camera-alignment | 84.8 | 70.1 |
| pedestrian-alignment-network-for-large-scale | 75.94 | 66.74 |
| learning-disentangled-representation-for | 90.0 | 79.5 |
| image-image-domain-adaptation-with-preserved | 46.4 | 26.2 |
| horizontal-pyramid-matching-for-person-re | 86.6 | 74.3 |
| enhancing-person-re-identification-via | 91.3 | 85.0 |
| person-re-identification-with-bias-controlled | 85.2 | 74.8 |
| image-based-and-partially-categorical | 94.39 | 83.58 |
| svdnet-for-pedestrian-retrieval | 76.7 | 56.8 |
| towards-better-validity-dispersion-based | 51.5 | 30 |
| joint-discriminative-and-generative-learning | 86.6 | 74.8 |
| person-re-identification-with-deep-similarity | - | 68.2 |
| fd-gan-pose-guided-feature-distilling-gan-for | 80.0 | 64.5 |
| multi-task-learning-with-coarse-priors-for | 91.5 | 82 |
| adaptivereid-adaptive-l2-regularization-in | 90.2 | 81.0 |
| beyond-human-parts-dual-part-aligned | 86.5 | 73.1 |
| beyond-part-models-person-retrieval-with | 83.3 | 69.2 |
| cluster-level-feature-alignment-for-person-re | 91.11 | 81.84 |
| spatial-temporal-person-re-identification | 94.5 | 92.7 |
| remix-training-generalized-person-re | 89.6 | 79.8 |
| unsupervised-tracklet-person-re | 62.3 | 44.6 |
| attrimeter-an-attribute-guided-metric | 90.2 | 79.1 |
| flipreid-closing-the-gap-between-training-and | 90.9 | 81.5 |
| camera-style-adaptation-for-person-re | 72.31 | 51.83 |
| devil-s-in-the-detail-graph-based-key-point | 90.89 | 81.29 |
| dense-interaction-learning-for-video-based | - | 97.1 |
| scalable-person-re-identification-a-benchmark | 25.13 | 12.17 |
| attention-network-robustification-for-person | 89.8 | 80.3 |
| a-pose-sensitive-embedding-for-person-re | 85.2 | 79.8 |
| fpb-feature-pyramid-branch-for-person-re | 91.2 | 82.9 |
| pointnet-deep-hierarchical-feature-learning | 60.23 | 39.36 |
| a-strong-baseline-and-batch-normalization | 90.1 | 79.1 |
| dip-learning-discriminative-implicit-parts | 91.7 | 85.2 |
| person-re-identification-via-attention | 90.4 | 81.5 |
| random-erasing-data-augmentation | 79.3 | 62.4 |
| an-effective-data-augmentation-for-person-re | 94.3 | 92.7 |
| learning-instance-level-spatial-temporal | - | 89.1 |
| a-discriminatively-learned-cnn-embedding-for | 68.9 | 49.3 |
| body-part-based-representation-learning-for | 92.4 | 84.2 |
| large-scale-pre-training-for-person-re | 92.0 | 84.3 |