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/CAL

CAL

Reported on 74 benchmarks across 9 tasks · 3 papers · 38 SOTA

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

Computer Vision40 results

Person Re-IdentificationonVC-Clothes
Rank-1· 2022-04-14
85.8
best: 87.1 (CAL+DLCR)
SOTA
Clothes-Changing Person Re-identification with RGB Modality Only arXiv:2204.06890
Person Re-IdentificationonVC-Clothes
mAP· 2022-04-14
79.8
best: 83.1 (Transreid+CCUP)
SOTA
Clothes-Changing Person Re-identification with RGB Modality Only arXiv:2204.06890
Person Re-IdentificationonLTCC
Rank-1· 2022-04-14
40.1
SOTA
Clothes-Changing Person Re-identification with RGB Modality Only arXiv:2204.06890
Person Re-IdentificationonLTCC
mAP· 2022-04-14
18
SOTA
Clothes-Changing Person Re-identification with RGB Modality Only arXiv:2204.06890
Person Re-IdentificationonCCVID
Rank-1· 2022-04-14
81.7
SOTA
Clothes-Changing Person Re-identification with RGB Modality Only arXiv:2204.06890
Person Re-IdentificationonCCVID
mAP· 2022-04-14
79.6
best: 90.9 (CSCI)
SOTA
Clothes-Changing Person Re-identification with RGB Modality Only arXiv:2204.06890
Person Re-IdentificationonPRCC
Rank-1· 2022-04-14
55.2
best: 84.6 (CAL+GEFF+DLCR)
SOTA
Clothes-Changing Person Re-identification with RGB Modality Only arXiv:2204.06890
Person Re-IdentificationonPRCC
mAP· 2022-04-14
55.8
best: 66 (CAL+GEFF+DLCR)
SOTA
Clothes-Changing Person Re-identification with RGB Modality Only arXiv:2204.06890
Intelligent SurveillanceonVehicleID Large
mAP· 2021-08-19
80.9
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Intelligent SurveillanceonVehicleID Medium
mAP· 2021-08-19
83.8
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Vehicle Re-IdentificationonVehicleID Large
mAP· 2021-08-19
80.9
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Vehicle Re-IdentificationonVehicleID Medium
mAP· 2021-08-19
83.8
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Person Re-IdentificationonMarket-1501
Rank-1· 2021-08-19
95.5
best: 98 (st-ReID(RE, RK))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Person Re-IdentificationonMarket-1501
mAP· 2021-08-19
89.5
best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Person Re-IdentificationonDukeMTMC-reID
Rank-1· 2021-08-19
90
best: 95.6 (CTL Model (ResNet50, 256x128))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Person Re-IdentificationonDukeMTMC-reID
mAP· 2021-08-19
80.5
best: 97.1 (DenseIL)
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Image ClassificationonFGVC Aircraft
Accuracy· 2021-08-19
94.2
best: 95.4 (SR-GNN)
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Image ClassificationonCUB-200-2011
Accuracy· 2021-08-19
90.6
best: 92.8 (PIM)
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Intelligent SurveillanceonVehicleID Large
Rank-1· 2021-08-19
75.1
best: 94.7 (Recall@k Surrogate loss (ViT-B/16))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Intelligent SurveillanceonVehicleID Medium
Rank-1· 2021-08-19
78.2
best: 95.2 (Recall@k Surrogate loss (ViT-B/16))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Intelligent SurveillanceonVeRi-776
Rank-1· 2021-08-19
95.4
best: 98 (MBR4B-LAI (w/ RK))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Intelligent SurveillanceonVeRi-776
Rank5· 2021-08-19
97.9
best: 99 (MBR4B-LAI (without re-ranking))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Intelligent SurveillanceonVeRi-776
mAP· 2021-08-19
74.3
best: 92.1 (MBR4B-LAI (w/ RK))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Intelligent SurveillanceonVehicleID Small
Rank-1· 2021-08-19
82.5
best: 96.2 (Recall@k Surrogate loss (ViT-B/16))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Intelligent SurveillanceonVehicleID Small
mAP· 2021-08-19
87.8
best: 92.5 (MBR-4B (without RK))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Fine-Grained Image ClassificationonFGVC Aircraft
Accuracy· 2021-08-19
94.2
best: 95.4 (SR-GNN)
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Fine-Grained Image ClassificationonCUB-200-2011
Accuracy· 2021-08-19
90.6
best: 92.8 (PIM)
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Vehicle Re-IdentificationonVehicleID Large
Rank-1· 2021-08-19
75.1
best: 94.7 (Recall@k Surrogate loss (ViT-B/16))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Vehicle Re-IdentificationonVehicleID Medium
Rank-1· 2021-08-19
78.2
best: 95.2 (Recall@k Surrogate loss (ViT-B/16))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Vehicle Re-IdentificationonVeRi-776
Rank-1· 2021-08-19
95.4
best: 98 (MBR4B-LAI (w/ RK))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Vehicle Re-IdentificationonVeRi-776
Rank5· 2021-08-19
97.9
best: 99 (MBR4B-LAI (without re-ranking))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Vehicle Re-IdentificationonVeRi-776
mAP· 2021-08-19
74.3
best: 92.1 (MBR4B-LAI (w/ RK))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Vehicle Re-IdentificationonVehicleID Small
Rank-1· 2021-08-19
82.5
best: 96.2 (Recall@k Surrogate loss (ViT-B/16))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Vehicle Re-IdentificationonVehicleID Small
mAP· 2021-08-19
87.8
best: 92.5 (MBR-4B (without RK))
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Image ClassificationonCIFAR-10N-Random2
Accuracy (mean)· 2021-02-10
90.75
best: 96.21 (PSSCL)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Image ClassificationonCIFAR-10N-Random3
Accuracy (mean)· 2021-02-10
90.74
best: 96.49 (PSSCL)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Image ClassificationonCIFAR-10N-Aggregate
Accuracy (mean)· 2021-02-10
91.97
best: 97.39 (ProMix)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Image ClassificationonCIFAR-10N-Random1
Accuracy (mean)· 2021-02-10
90.93
best: 96.97 (ProMix)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Image ClassificationonCIFAR-100N
Accuracy (mean)· 2021-02-10
61.73
best: 74.08 (PGDF)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Image ClassificationonCIFAR-10N-Worst
Accuracy (mean)· 2021-02-10
85.36
best: 96.16 (ProMix)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291

Methodology28 results

Few-Shot LearningonStanford Cars
12-shot Accuracy· 2021-08-19
82.9
best: 88.8 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonStanford Cars
16-shot Accuracy· 2021-08-19
88.9
best: 91 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonStanford Cars
4-shot Accuracy· 2021-08-19
42.2
best: 66.7 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonStanford Cars
8-shot Accuracy· 2021-08-19
71.8
best: 82.6 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonFGVC Aircraft
12-shot Accuracy· 2021-08-19
67.6
best: 75.4 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonFGVC Aircraft
16-shot Accuracy· 2021-08-19
74.3
best: 78.9 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonFGVC Aircraft
4-shot Accuracy· 2021-08-19
35.2
best: 52.2 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonFGVC Aircraft
8-shot Accuracy· 2021-08-19
55.4
best: 67.2 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonFGVC Aircraft
Harmonic mean· 2021-08-19
35.2
best: 52.2 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonDTD
12-shot Accuracy· 2021-08-19
54.6
best: 58.1 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonDTD
16-shot Accuracy· 2021-08-19
57.4
best: 60.2 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonDTD
4-shot Accuracy· 2021-08-19
40.9
best: 48.3 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Few-Shot LearningonDTD
8-shot Accuracy· 2021-08-19
50.4
best: 54.8 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonStanford Cars
12-shot Accuracy· 2021-08-19
82.9
best: 88.8 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonStanford Cars
16-shot Accuracy· 2021-08-19
88.9
best: 91 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonStanford Cars
4-shot Accuracy· 2021-08-19
42.2
best: 66.7 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonStanford Cars
8-shot Accuracy· 2021-08-19
71.8
best: 82.6 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonFGVC Aircraft
12-shot Accuracy· 2021-08-19
67.6
best: 75.4 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonFGVC Aircraft
16-shot Accuracy· 2021-08-19
74.3
best: 78.9 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonFGVC Aircraft
4-shot Accuracy· 2021-08-19
35.2
best: 52.2 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonFGVC Aircraft
8-shot Accuracy· 2021-08-19
55.4
best: 67.2 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonFGVC Aircraft
Harmonic mean· 2021-08-19
35.2
best: 52.2 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonDTD
12-shot Accuracy· 2021-08-19
54.6
best: 58.1 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonDTD
16-shot Accuracy· 2021-08-19
57.4
best: 60.2 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonDTD
4-shot Accuracy· 2021-08-19
40.9
best: 48.3 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
Meta-LearningonDTD
8-shot Accuracy· 2021-08-19
50.4
best: 54.8 (SaSPA + CAL)
SOTA
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
ClassificationonFGVC Aircraft
OOD Accuracy (%)· 2021-08-19
10.2
best: 41.5 (CAL + SaSPA)
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728
ClassificationonFGVC Aircraft
Top-1 Accuracy (%)· 2021-08-19
71
best: 73 (CAL + SaSPA)
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification arXiv:2108.08728

Medical6 results

Document Text ClassificationonCIFAR-10N-Random2
Accuracy (mean)· 2021-02-10
90.75
best: 96.21 (PSSCL)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Document Text ClassificationonCIFAR-10N-Random3
Accuracy (mean)· 2021-02-10
90.74
best: 96.49 (PSSCL)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Document Text ClassificationonCIFAR-10N-Aggregate
Accuracy (mean)· 2021-02-10
91.97
best: 97.39 (ProMix)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Document Text ClassificationonCIFAR-10N-Random1
Accuracy (mean)· 2021-02-10
90.93
best: 96.97 (ProMix)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Document Text ClassificationonCIFAR-100N
Accuracy (mean)· 2021-02-10
61.73
best: 74.08 (PGDF)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291
Document Text ClassificationonCIFAR-10N-Worst
Accuracy (mean)· 2021-02-10
85.36
best: 96.16 (ProMix)
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels arXiv:2102.05291