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/CLIPCleaner

CLIPCleaner

Reported on 12 benchmarks across 2 tasks · 1 paper

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

Computer Vision6 results

Image ClassificationonRed MiniImageNet 80% label noise
Test Accuracy· 2024-08-19
43.82
best: 51.2 (NCR (ResNet-18))
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Image ClassificationonANIMAL
Accuracy· 2024-08-19
88.85
best: 89 (Jigsaw-ViT)
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Image ClassificationonRed MiniImageNet 40% label noise
Test Accuracy· 2024-08-19
58.42
best: 64.6 (NCR (ResNet-18))
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Image ClassificationonClothing1M
Test Accuracy· 2024-08-19
74.87
best: 75.2 (Knockoffs-SPR)
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Image ClassificationonRed MiniImageNet 60% label noise
Test Accuracy· 2024-08-19
53.18
best: 53.21 (InstanceGM-SS)
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Image ClassificationonRed MiniImageNet 20% label noise
Test Accuracy· 2024-08-19
61.44
best: 69 (NCR (ResNet-18))
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012

Medical6 results

Document Text ClassificationonRed MiniImageNet 80% label noise
Test Accuracy· 2024-08-19
43.82
best: 51.2 (NCR (ResNet-18))
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Document Text ClassificationonANIMAL
Accuracy· 2024-08-19
88.85
best: 89 (Jigsaw-ViT)
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Document Text ClassificationonRed MiniImageNet 40% label noise
Test Accuracy· 2024-08-19
58.42
best: 64.6 (NCR (ResNet-18))
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Document Text ClassificationonClothing1M
Test Accuracy· 2024-08-19
74.87
best: 75.2 (Knockoffs-SPR)
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Document Text ClassificationonRed MiniImageNet 60% label noise
Test Accuracy· 2024-08-19
53.18
best: 53.21 (InstanceGM-SS)
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012
Document Text ClassificationonRed MiniImageNet 20% label noise
Test Accuracy· 2024-08-19
61.44
best: 69 (NCR (ResNet-18))
CLIPCleaner: Cleaning Noisy Labels with CLIP arXiv:2408.10012