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/MobileNetV2

MobileNetV2

Reported on 32 benchmarks across 12 tasks · 6 papers · 1 SOTA

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

Computer Vision13 results

Parking Space OccupancyonAction-Camera Parking
F1-score· 2023-06-07
0.9343
SOTA
Revising deep learning methods in parking lot occupancy detection arXiv:2306.04288
Parking Space OccupancyonSPKL
F1-score· 2023-06-07
0.6937
best: 0.7393 (EfficientNet-P)
Revising deep learning methods in parking lot occupancy detection arXiv:2306.04288
Parking Space OccupancyonACMPS
F1-score· 2023-06-07
0.9971
best: 0.9982 (EfficientNet-P)
Revising deep learning methods in parking lot occupancy detection arXiv:2306.04288
Parking Space OccupancyonCNRPark+EXT
F1-score· 2023-06-07
0.9663
best: 0.9683 (EfficientNet-P)
Revising deep learning methods in parking lot occupancy detection arXiv:2306.04288
Face Reconstructionon300W
NME_inter-ocular (%, Challenge)· 2021-02-27
7.35
best: 8.2 (ASMNet)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
Face Reconstructionon300W
NME_inter-ocular (%, Common)· 2021-02-27
3.88
best: 5.09 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
Face Reconstructionon300W
NME_inter-ocular (%, Full)· 2021-02-27
4.59
best: 5.63 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
Face ReconstructiononWFLW
NME (inter-ocular)· 2021-02-27
9.41
best: 11.13 (ESR)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3D Face Reconstructionon300W
NME_inter-ocular (%, Challenge)· 2021-02-27
7.35
best: 8.2 (ASMNet)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3D Face Reconstructionon300W
NME_inter-ocular (%, Common)· 2021-02-27
3.88
best: 5.09 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3D Face Reconstructionon300W
NME_inter-ocular (%, Full)· 2021-02-27
4.59
best: 5.63 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3D Face ReconstructiononWFLW
NME (inter-ocular)· 2021-02-27
9.41
best: 11.13 (ESR)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
Image ClassificationonImageNet
GFLOPs· uses extra data· 2018-01-13
0.6
best: 1478 (InternImage-H)
MobileNetV2: Inverted Residuals and Linear Bottlenecks arXiv:1801.04381

Methodology9 results

Network PruningonImageNet
Accuracy· 2021-08-02
73.42
best: 78.79 (ResNet50-2.3 GFLOPs)
Group Fisher Pruning for Practical Network Compression arXiv:2108.00708
Network PruningonImageNet
GFLOPs· 2021-08-02
0.29
best: 2.5 (ResNet50 2.5 GFLOPS)
Group Fisher Pruning for Practical Network Compression arXiv:2108.00708
Network PruningonImageNet
MParams· 2021-08-02
3.31
best: 14.811 (ResNet50-2.3 GFLOPs)
Group Fisher Pruning for Practical Network Compression arXiv:2108.00708
3Don300W
NME_inter-ocular (%, Challenge)· 2021-02-27
7.35
best: 8.2 (ASMNet)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3Don300W
NME_inter-ocular (%, Common)· 2021-02-27
3.88
best: 5.09 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3Don300W
NME_inter-ocular (%, Full)· 2021-02-27
4.59
best: 5.63 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3DonWFLW
NME (inter-ocular)· 2021-02-27
9.41
best: 11.13 (ESR)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
QuantizationonImageNet
Top-1 Accuracy (%)· 2020-07-20
70.9
best: 85.03 (FQ-ViT (ViT-L))
HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs arXiv:2007.09952
2D Object DetectiononCIMAT-Cyclist
mAP@0.50· 2020-04-25
0.899
best: 0.918 (SSD InceptionV2)
On the safety of vulnerable road users by cyclist orientation detection using Deep Learning arXiv:2004.11909

Medical5 results

3D Face Modellingon300W
NME_inter-ocular (%, Challenge)· 2021-02-27
7.35
best: 8.2 (ASMNet)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3D Face Modellingon300W
NME_inter-ocular (%, Common)· 2021-02-27
3.88
best: 5.09 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3D Face Modellingon300W
NME_inter-ocular (%, Full)· 2021-02-27
4.59
best: 5.63 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
3D Face ModellingonWFLW
NME (inter-ocular)· 2021-02-27
9.41
best: 11.13 (ESR)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
Semantic SegmentationonDADA-seg
mIoU· 2018-01-13
16.05
best: 46.97 (MMUDA)
MobileNetV2: Inverted Residuals and Linear Bottlenecks arXiv:1801.04381

Music4 results

Facial Recognition and Modellingon300W
NME_inter-ocular (%, Challenge)· 2021-02-27
7.35
best: 8.2 (ASMNet)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
Facial Recognition and Modellingon300W
NME_inter-ocular (%, Common)· 2021-02-27
3.88
best: 5.09 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
Facial Recognition and Modellingon300W
NME_inter-ocular (%, Full)· 2021-02-27
4.59
best: 5.63 (3DDFA)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119
Facial Recognition and ModellingonWFLW
NME (inter-ocular)· 2021-02-27
9.41
best: 11.13 (ESR)
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation arXiv:2103.00119

Audio1 result

10-shot image generationonDADA-seg
mIoU· 2018-01-13
16.05
best: 46.97 (MMUDA)
MobileNetV2: Inverted Residuals and Linear Bottlenecks arXiv:1801.04381