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/InstanceGM

InstanceGM

Reported on 18 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision11 results

Image ClassificationonCIFAR-10
Test Accuracy· 2022-09-02
95.9
SOTA
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonCIFAR-100
Test Accuracy· 2022-09-02
77.19
SOTA
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonRed MiniImageNet 20% label noise
Accuracy· 2022-09-02
58.38
best: 69 (NCR (ResNet-18))
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonRed MiniImageNet 60% label noise
Accuracy· 2022-09-02
47.96
best: 53.21 (InstanceGM-SS)
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonRed MiniImageNet 40% label noise
Accuracy· 2022-09-02
52.24
best: 64.6 (NCR (ResNet-18))
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonRed MiniImageNet 80% label noise
Accuracy· 2022-09-02
39.62
best: 51.2 (NCR (ResNet-18))
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonRed MiniImageNet 80% label noise
Test Accuracy· 2022-09-02
39.62
best: 51.2 (NCR (ResNet-18))
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonANIMAL
Accuracy· 2022-09-02
84.6
best: 89 (Jigsaw-ViT)
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonRed MiniImageNet 40% label noise
Test Accuracy· 2022-09-02
52.24
best: 64.6 (NCR (ResNet-18))
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonRed MiniImageNet 60% label noise
Test Accuracy· 2022-09-02
47.96
best: 53.21 (InstanceGM-SS)
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Image ClassificationonRed MiniImageNet 20% label noise
Test Accuracy· 2022-09-02
58.38
best: 69 (NCR (ResNet-18))
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906

Medical7 results

Document Text ClassificationonCIFAR-10
Test Accuracy· 2022-09-02
95.9
SOTA
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Document Text ClassificationonCIFAR-100
Test Accuracy· 2022-09-02
77.19
SOTA
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Document Text ClassificationonRed MiniImageNet 80% label noise
Test Accuracy· 2022-09-02
39.62
best: 51.2 (NCR (ResNet-18))
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Document Text ClassificationonANIMAL
Accuracy· 2022-09-02
84.6
best: 89 (Jigsaw-ViT)
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Document Text ClassificationonRed MiniImageNet 40% label noise
Test Accuracy· 2022-09-02
52.24
best: 64.6 (NCR (ResNet-18))
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Document Text ClassificationonRed MiniImageNet 60% label noise
Test Accuracy· 2022-09-02
47.96
best: 53.21 (InstanceGM-SS)
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906
Document Text ClassificationonRed MiniImageNet 20% label noise
Test Accuracy· 2022-09-02
58.38
best: 69 (NCR (ResNet-18))
Instance-Dependent Noisy Label Learning via Graphical Modelling arXiv:2209.00906