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/PNP Loss

PNP Loss

Reported on 16 benchmarks across 3 tasks · 1 paper · 10 SOTA

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

Computer Vision16 results

Intelligent SurveillanceonVehicleID Large
Rank-1· 2021-02-09
93.2
best: 94.7 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Intelligent SurveillanceonVehicleID Large
Rank-5· 2021-02-09
96.6
best: 97.1 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Intelligent SurveillanceonVehicleID Medium
Rank-1· 2021-02-09
94.2
best: 95.2 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Intelligent SurveillanceonVehicleID Medium
Rank-5· 2021-02-09
96.9
best: 97.2 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Intelligent SurveillanceonVehicleID Small
Rank-1· 2021-02-09
95.5
best: 96.2 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Vehicle Re-IdentificationonVehicleID Large
Rank-1· 2021-02-09
93.2
best: 94.7 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Vehicle Re-IdentificationonVehicleID Large
Rank-5· 2021-02-09
96.6
best: 97.1 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Vehicle Re-IdentificationonVehicleID Medium
Rank-1· 2021-02-09
94.2
best: 95.2 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Vehicle Re-IdentificationonVehicleID Medium
Rank-5· 2021-02-09
96.9
best: 97.2 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Vehicle Re-IdentificationonVehicleID Small
Rank-1· 2021-02-09
95.5
best: 96.2 (Recall@k Surrogate loss (ViT-B/16))
SOTA
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Image RetrievalonSOP
R@1· 2021-02-09
81.1
best: 91.2 (Unicom+ViT-L@336px)
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Image RetrievaloniNaturalist
R@1· 2021-02-09
66.6
best: 88.9 (Unicom+ViT-L@336px)
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Image RetrievaloniNaturalist
R@16· 2021-02-09
89.7
best: 95.9 (Recall@k Surrogate loss (ViT-B/16))
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Image RetrievaloniNaturalist
R@32· 2021-02-09
92.6
best: 97.2 (Recall@k Surrogate loss (ViT-B/16))
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Intelligent SurveillanceonVehicleID Small
Rank-5· 2021-02-09
97.8
best: 98 (Recall@k Surrogate loss (ViT-B/16))
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640
Vehicle Re-IdentificationonVehicleID Small
Rank-5· 2021-02-09
97.8
best: 98 (Recall@k Surrogate loss (ViT-B/16))
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough arXiv:2102.04640