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/Xception

Xception

Reported on 14 benchmarks across 6 tasks · 2 papers · 8 SOTA

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

Medical12 results

3D Shape Reconstruction from VideosonFakeAVCeleb
AP· 2019-01-25
84.8
best: 96.8 (FACTOR)
SOTA
FaceForensics++: Learning to Detect Manipulated Facial Images arXiv:1901.08971
3D Shape Reconstruction from VideosonFakeAVCeleb
ROC AUC· 2019-01-25
85.3
best: 97.4 (FACTOR)
SOTA
FaceForensics++: Learning to Detect Manipulated Facial Images arXiv:1901.08971
Disease PredictiononSrinivasan2014
Acc· 2019-10-13
99.36
best: 100 (OpticNet-71)
Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images arXiv:1910.05672
Disease PredictiononSrinivasan2014
Acc· 2019-10-13
99.36
best: 100 (OpticNet-71)
Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images arXiv:1910.05672
Medical DiagnosisonSrinivasan2014
Acc· 2019-10-13
99.36
best: 100 (OpticNet-71)
Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images arXiv:1910.05672
Medical DiagnosisonSrinivasan2014
Acc· 2019-10-13
99.36
best: 100 (OpticNet-71)
Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images arXiv:1910.05672
Disease PredictiononOCT2017
Acc
99.7
best: 100 (UniNet)
Disease PredictiononOCT2017
Sensitivity
99.7
best: 99.8 (OpticNet-71)
Disease PredictiononOCT2017
Sensitivity
99.7
best: 99.8 (OpticNet-71)
Medical DiagnosisonOCT2017
Acc
99.7
best: 100 (UniNet)
Medical DiagnosisonOCT2017
Sensitivity
99.7
best: 99.8 (OpticNet-71)
Medical DiagnosisonOCT2017
Sensitivity
99.7
best: 99.8 (OpticNet-71)

Methodology4 results

3D ReconstructiononFakeAVCeleb
AP· 2019-01-25
84.8
best: 96.8 (FACTOR)
SOTA
FaceForensics++: Learning to Detect Manipulated Facial Images arXiv:1901.08971
3D ReconstructiononFakeAVCeleb
ROC AUC· 2019-01-25
85.3
best: 97.4 (FACTOR)
SOTA
FaceForensics++: Learning to Detect Manipulated Facial Images arXiv:1901.08971
3DonFakeAVCeleb
AP· 2019-01-25
84.8
best: 96.8 (FACTOR)
SOTA
FaceForensics++: Learning to Detect Manipulated Facial Images arXiv:1901.08971
3DonFakeAVCeleb
ROC AUC· 2019-01-25
85.3
best: 97.4 (FACTOR)
SOTA
FaceForensics++: Learning to Detect Manipulated Facial Images arXiv:1901.08971

Audio2 results

DeepFake DetectiononFakeAVCeleb
AP· 2019-01-25
84.8
best: 96.8 (FACTOR)
SOTA
FaceForensics++: Learning to Detect Manipulated Facial Images arXiv:1901.08971
DeepFake DetectiononFakeAVCeleb
ROC AUC· 2019-01-25
85.3
best: 97.4 (FACTOR)
SOTA
FaceForensics++: Learning to Detect Manipulated Facial Images arXiv:1901.08971