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/CC

CC

Reported on 25 benchmarks across 4 tasks · 3 papers · 13 SOTA

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

Computer Vision24 results

Image ClusteringonImageNet-10
ARI· 2020-09-21
0.822
best: 0.935 (DPAC)
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonImageNet-10
Accuracy· 2020-09-21
0.893
best: 0.992 (TAC)
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonImageNet-10
Image Size· 2020-09-21
224
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonImageNet-10
NMI· 2020-09-21
0.859
best: 0.985 (TAC)
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonTiny-ImageNet
ARI· 2020-09-21
0.071
best: 0.5227 (ITAE)
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonTiny-ImageNet
NMI· 2020-09-21
0.34
best: 0.8178 (ITAE)
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonSTL-10
Accuracy· uses extra data· 2020-09-21
0.85
best: 0.997 (TURTLE (CLIP + DINOv2))
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonSTL-10
NMI· uses extra data· 2020-09-21
0.764
best: 0.993 (TURTLE (CLIP + DINOv2))
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonImagenet-dog-15
ARI· 2020-09-21
0.274
best: 0.879 (MAE-CT (best))
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonImagenet-dog-15
Accuracy· 2020-09-21
0.429
best: 0.943 (MAE-CT (best))
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonImagenet-dog-15
Image Size· 2020-09-21
224
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonImagenet-dog-15
NMI· 2020-09-21
0.445
best: 0.904 (MAE-CT (best))
SOTA
Contrastive Clustering arXiv:2009.09687
Image ClusteringonTiny-ImageNet
Accuracy· 2018-05-24
0.14
best: 0.698 (PRO-DSC)
SOTA
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation arXiv:1805.09806
Image Classificationonmini WebVision 1.0
ImageNet Top-1 Accuracy· 2022-07-29
76.08
best: 82.56 (LRA-diffusion (CLIP ViT))
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels arXiv:2207.14476
Image Classificationonmini WebVision 1.0
ImageNet Top-5 Accuracy· 2022-07-29
93.86
best: 97.24 (RTE (Inception-ResNet-v2))
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels arXiv:2207.14476
Image Classificationonmini WebVision 1.0
Top-1 Accuracy· 2022-07-29
79.36
best: 84.16 (LRA-diffusion (CLIP ViT))
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels arXiv:2207.14476
Image Classificationonmini WebVision 1.0
Top-5 Accuracy· 2022-07-29
93.64
best: 94.84 (PSSCL (130 epochs))
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels arXiv:2207.14476
Image ClusteringonCIFAR-10
ARI· 2020-09-21
0.637
best: 0.989 (TURTLE (CLIP + DINOv2))
Contrastive Clustering arXiv:2009.09687
Image ClusteringonCIFAR-10
Accuracy· 2020-09-21
0.79
best: 0.995 (TURTLE (CLIP + DINOv2))
Contrastive Clustering arXiv:2009.09687
Image ClusteringonCIFAR-10
NMI· 2020-09-21
0.705
best: 0.985 (TURTLE (CLIP + DINOv2))
Contrastive Clustering arXiv:2009.09687
Image ClusteringonCIFAR-100
ARI· 2020-09-21
0.266
best: 0.834 (TURTLE (CLIP + DINOv2))
Contrastive Clustering arXiv:2009.09687
Image ClusteringonCIFAR-100
Accuracy· 2020-09-21
0.429
best: 0.898 (TURTLE (CLIP + DINOv2))
Contrastive Clustering arXiv:2009.09687
Image ClusteringonCIFAR-100
NMI· 2020-09-21
0.431
best: 0.915 (TURTLE (CLIP + DINOv2))
Contrastive Clustering arXiv:2009.09687
Depth EstimationonKITTI Eigen split
absolute relative error· 2018-05-24
0.14
best: 0.029 (SPIDepth)
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation arXiv:1805.09806

Methodology1 result

3DonKITTI Eigen split
absolute relative error· 2018-05-24
0.14
best: 0.029 (SPIDepth)
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation arXiv:1805.09806