Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PDA-Net

PDA-Net

Reported on 24 benchmarks across 4 tasks · 2 papers

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision8 results

Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2021-05-25
84.2
best: 98.8 (CAML [Laion-2b])
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images arXiv:2105.11874
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2021-05-25
63.84
best: 97.95 (SgVA-CLIP)
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images arXiv:2105.11874
Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2021-05-25
69.01
best: 96.8 (CAML [Laion-2b])
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images arXiv:2105.11874
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2021-05-25
83.11
best: 98.72 (SgVA-CLIP)
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images arXiv:2105.11874
Few-Shot Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy· 2021-05-25
84.2
best: 98.8 (CAML [Laion-2b])
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images arXiv:2105.11874
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2021-05-25
63.84
best: 97.95 (SgVA-CLIP)
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images arXiv:2105.11874
Few-Shot Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy· 2021-05-25
69.01
best: 96.8 (CAML [Laion-2b])
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images arXiv:2105.11874
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2021-05-25
83.11
best: 98.72 (SgVA-CLIP)
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images arXiv:2105.11874

Methodology8 results

Domain AdaptationonMarket to Duke
mAP· 2019-09-20
45.1
best: 74.8 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Domain AdaptationonMarket to Duke
rank-1· 2019-09-20
63.2
best: 85 (CCTSE)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Domain AdaptationonMarket to Duke
rank-10· 2019-09-20
82.5
best: 94.4 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Domain AdaptationonMarket to Duke
rank-5· 2019-09-20
77
best: 92.4 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Domain AdaptationonDuke to Market
mAP· 2019-09-20
47.6
best: 84.4 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Domain AdaptationonDuke to Market
rank-1· 2019-09-20
75.2
best: 93.6 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Domain AdaptationonDuke to Market
rank-10· 2019-09-20
90.2
best: 98.7 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Domain AdaptationonDuke to Market
rank-5· 2019-09-20
86.3
best: 97.7 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675

Other8 results

Unsupervised Domain AdaptationonMarket to Duke
mAP· 2019-09-20
45.1
best: 74.8 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Unsupervised Domain AdaptationonMarket to Duke
rank-1· 2019-09-20
63.2
best: 85 (CCTSE)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Unsupervised Domain AdaptationonMarket to Duke
rank-10· 2019-09-20
82.5
best: 94.4 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Unsupervised Domain AdaptationonMarket to Duke
rank-5· 2019-09-20
77
best: 92.4 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Unsupervised Domain AdaptationonDuke to Market
mAP· 2019-09-20
47.6
best: 84.4 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Unsupervised Domain AdaptationonDuke to Market
rank-1· 2019-09-20
75.2
best: 93.6 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Unsupervised Domain AdaptationonDuke to Market
rank-10· 2019-09-20
90.2
best: 98.7 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675
Unsupervised Domain AdaptationonDuke to Market
rank-5· 2019-09-20
86.3
best: 97.7 (CORE-ReID)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation arXiv:1909.09675