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/ResNet-18

ResNet-18

Reported on 37 benchmarks across 10 tasks · 11 papers · 14 SOTA

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

Computer Vision20 results

Gaze EstimationonGaze360
Angular Error· 2021-05-20
12.94
best: 10.02 (MCGaze)
SOTA
Weakly-Supervised Physically Unconstrained Gaze Estimation arXiv:2105.09803
Gaze EstimationonGaze360
Angular Error· 2019-10-22
13.5
best: 10.02 (MCGaze)
SOTA
Gaze360: Physically Unconstrained Gaze Estimation in the Wild arXiv:1910.10088
Domain GeneralizationonNICO Vehicle
Accuracy· 2019-03-16
77.39
best: 81.59 (NAS-OoD)
SOTA
Domain Generalization by Solving Jigsaw Puzzles arXiv:1903.06864
Image ClassificationonFashion-MNIST
Accuracy· 2024-11-15
92.28
best: 99.06 (pFedBreD_ns_mg)
Vision Eagle Attention: a new lens for advancing image classification arXiv:2411.10564
Image ClassificationonFashion-MNIST
Percentage error· 2024-11-15
7.72
best: 3.64 (PreAct-ResNet18 + FMix)
Vision Eagle Attention: a new lens for advancing image classification arXiv:2411.10564
Image ClassificationonOracle-MNIST
Accuracy· 2024-11-15
96.77
best: 97.2 (ResNet-18 + Vision Eagle Attention)
Vision Eagle Attention: a new lens for advancing image classification arXiv:2411.10564
Image ClassificationonIntel Image Classification
Accuracy· 2024-11-15
90.93
best: 92.43 (ResNet-18 + Vision Eagle Attention)
Vision Eagle Attention: a new lens for advancing image classification arXiv:2411.10564
Image ClassificationonCIFAR-10
Percentage correct· 2022-06-27
95.55
best: 99.5 (ViT-H/14)
Benchopt: Reproducible, efficient and collaborative optimization benchmarks arXiv:2206.13424
Image ClassificationonSVHN
Percentage error· 2022-06-27
2.65
best: 1 (E2E-M3)
Benchopt: Reproducible, efficient and collaborative optimization benchmarks arXiv:2206.13424
Image ClassificationonDF20
F1 - macro· 2021-03-18
0.58
best: 0.743 (ViT-Large/16 (384))
Danish Fungi 2020 -- Not Just Another Image Recognition Dataset arXiv:2103.10107
Image ClassificationonDF20
Top-1· 2021-03-18
67.13
best: 80.45 (ViT-Large/16 (384))
Danish Fungi 2020 -- Not Just Another Image Recognition Dataset arXiv:2103.10107
Image ClassificationonDF20
Top-3· 2021-03-18
82.65
best: 91.68 (ViT-Large/16 (384))
Danish Fungi 2020 -- Not Just Another Image Recognition Dataset arXiv:2103.10107
Image ClassificationonDF20 - Mini
F1 - macro· 2021-03-18
0.514
best: 0.669 (ViT-Large/16 (384))
Danish Fungi 2020 -- Not Just Another Image Recognition Dataset arXiv:2103.10107
Image ClassificationonDF20 - Mini
Top-1· 2021-03-18
62.91
best: 75.85 (ViT-Large/16 (384))
Danish Fungi 2020 -- Not Just Another Image Recognition Dataset arXiv:2103.10107
Image ClassificationonDF20 - Mini
Top-3· 2021-03-18
81.65
best: 89.95 (ViT-Large/16 (384))
Danish Fungi 2020 -- Not Just Another Image Recognition Dataset arXiv:2103.10107
Image ClassificationonCIFAR-10
Percentage correct· uses extra data· 2019-11-13
90.65
best: 99.5 (ViT-H/14)
Knowledge Representing: Efficient, Sparse Representation of Prior Knowledge for Knowledge Distillation arXiv:1911.05329
Image ClassificationonCINIC-10
Accuracy· 2018-10-02
90.27
best: 95.8 (VIT-L/16 (Spinal FC, Background))
CINIC-10 is not ImageNet or CIFAR-10 arXiv:1810.03505
Image ClassificationonGasHisSDB
Accuracy· 2015-12-10
98.47
best: 98.74 (CoAtNet-1)
Deep Residual Learning for Image Recognition arXiv:1512.03385
Image ClassificationonGasHisSDB
F1-Score· 2015-12-10
99.19
best: 99.38 (CoAtNet-1)
Deep Residual Learning for Image Recognition arXiv:1512.03385
Image ClassificationonGasHisSDB
Precision· 2015-12-10
99.94
best: 99.97 (CoAtNet-1)
Deep Residual Learning for Image Recognition arXiv:1512.03385

Methodology6 results

Ordinal ClassificationonOASIS+NACC+ICBM+ABIDE+IXI
Mean absolute error· 2023-10-25
2.56
SOTA
Ordinal Classification with Distance Regularization for Robust Brain Age Prediction arXiv:2403.10522
Domain AdaptationonNICO Vehicle
Accuracy· 2019-03-16
77.39
best: 81.59 (NAS-OoD)
SOTA
Domain Generalization by Solving Jigsaw Puzzles arXiv:1903.06864
ClassificationonNCT-CRC-HE-100K
Accuracy (%)· 2015-12-10
92.66
best: 95.59 (Efficientnet-b0)
Deep Residual Learning for Image Recognition arXiv:1512.03385
ClassificationonNCT-CRC-HE-100K
F1-Score· 2015-12-10
95.23
best: 97.48 (Efficientnet-b0)
Deep Residual Learning for Image Recognition arXiv:1512.03385
ClassificationonNCT-CRC-HE-100K
Precision· 2015-12-10
99.9
best: 100 (ResNet-50)
Deep Residual Learning for Image Recognition arXiv:1512.03385
ClassificationonNCT-CRC-HE-100K
Specificity· 2015-12-10
99.08
best: 99.45 (Efficientnet-b0)
Deep Residual Learning for Image Recognition arXiv:1512.03385

Miscellaneous6 results

Image Retrieval with Multi-Modal QueryonSoundingEarth
Image-to-sound R@100· 2021-08-02
0.291
best: 0.434 (GeoCLAP)
SOTA
Self-supervised Audiovisual Representation Learning for Remote Sensing Data arXiv:2108.00688
Image Retrieval with Multi-Modal QueryonSoundingEarth
Median Rank· 2021-08-02
565
SOTA
Self-supervised Audiovisual Representation Learning for Remote Sensing Data arXiv:2108.00688
Image Retrieval with Multi-Modal QueryonSoundingEarth
Sound-to-image R@100· 2021-08-02
0.25
best: 0.434 (GeoCLAP)
SOTA
Self-supervised Audiovisual Representation Learning for Remote Sensing Data arXiv:2108.00688
Cross-Modal Information RetrievalonSoundingEarth
Image-to-sound R@100· 2021-08-02
0.291
best: 0.434 (GeoCLAP)
SOTA
Self-supervised Audiovisual Representation Learning for Remote Sensing Data arXiv:2108.00688
Cross-Modal Information RetrievalonSoundingEarth
Median Rank· 2021-08-02
565
SOTA
Self-supervised Audiovisual Representation Learning for Remote Sensing Data arXiv:2108.00688
Cross-Modal Information RetrievalonSoundingEarth
Sound-to-image R@100· 2021-08-02
0.25
best: 0.434 (GeoCLAP)
SOTA
Self-supervised Audiovisual Representation Learning for Remote Sensing Data arXiv:2108.00688

Medical4 results

Medical Image ClassificationonNCT-CRC-HE-100K
Accuracy (%)· 2015-12-10
92.66
best: 95.59 (Efficientnet-b0)
Deep Residual Learning for Image Recognition arXiv:1512.03385
Medical Image ClassificationonNCT-CRC-HE-100K
F1-Score· 2015-12-10
95.23
best: 97.48 (Efficientnet-b0)
Deep Residual Learning for Image Recognition arXiv:1512.03385
Medical Image ClassificationonNCT-CRC-HE-100K
Precision· 2015-12-10
99.9
best: 100 (ResNet-50)
Deep Residual Learning for Image Recognition arXiv:1512.03385
Medical Image ClassificationonNCT-CRC-HE-100K
Specificity· 2015-12-10
99.08
best: 99.45 (Efficientnet-b0)
Deep Residual Learning for Image Recognition arXiv:1512.03385

Natural Language Processing3 results

Cross-Modal RetrievalonSoundingEarth
Image-to-sound R@100· 2021-08-02
0.291
best: 0.434 (GeoCLAP)
SOTA
Self-supervised Audiovisual Representation Learning for Remote Sensing Data arXiv:2108.00688
Cross-Modal RetrievalonSoundingEarth
Median Rank· 2021-08-02
565
SOTA
Self-supervised Audiovisual Representation Learning for Remote Sensing Data arXiv:2108.00688
Cross-Modal RetrievalonSoundingEarth
Sound-to-image R@100· 2021-08-02
0.25
best: 0.434 (GeoCLAP)
SOTA
Self-supervised Audiovisual Representation Learning for Remote Sensing Data arXiv:2108.00688