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/SCNN

SCNN

Reported on 26 benchmarks across 4 tasks · 3 papers · 18 SOTA

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

Time Series16 results

Time Series ForecastingonETTm1 (192) Multivariate
MSE· 2023-05-22
0.327
best: 0.315 (xPatch)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series ForecastingonWeather (192)
MSE· 2023-05-22
0.188
best: 0.186 (SegRNN)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series ForecastingonETTm2 (96) Multivariate
MSE· 2023-05-22
0.163
best: 0.153 (xPatch)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series ForecastingonETTh1 (192) Multivariate
MAE· 2023-05-22
0.398
best: 0.394 (PatchMixer)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series ForecastingonETTh1 (192) Multivariate
MSE· 2023-05-22
0.379
best: 0.373 (PatchMixer)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series ForecastingonETTm1 (96) Multivariate
MSE· 2023-05-22
0.287
best: 0.275 (xPatch)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series ForecastingonWeather (96)
MSE· 2023-05-22
0.142
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series AnalysisonETTm1 (192) Multivariate
MSE· 2023-05-22
0.327
best: 0.315 (xPatch)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series AnalysisonWeather (192)
MSE· 2023-05-22
0.188
best: 0.186 (SegRNN)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series AnalysisonETTm2 (96) Multivariate
MSE· 2023-05-22
0.163
best: 0.153 (xPatch)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series AnalysisonETTh1 (192) Multivariate
MAE· 2023-05-22
0.398
best: 0.394 (PatchMixer)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series AnalysisonETTh1 (192) Multivariate
MSE· 2023-05-22
0.379
best: 0.373 (PatchMixer)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series AnalysisonETTm1 (96) Multivariate
MSE· 2023-05-22
0.287
best: 0.275 (xPatch)
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series AnalysisonWeather (96)
MSE· 2023-05-22
0.142
SOTA
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series ForecastingonETTm2 (192) Multivariate
MSE· 2023-05-22
0.221
best: 0.213 (xPatch)
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036
Time Series AnalysisonETTm2 (192) Multivariate
MSE· 2023-05-22
0.221
best: 0.213 (xPatch)
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting arXiv:2305.13036

Robots5 results

Autonomous VehiclesonCurveLanes
GFLOPs· 2020-07-23
328.4
SOTA
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending arXiv:2007.12147
Autonomous VehiclesonCULane
F1 score· uses extra data· 2017-12-17
71.6
best: 81.23 (DLNet)
SOTA
Spatial As Deep: Spatial CNN for Traffic Scene Understanding arXiv:1712.06080
Autonomous VehiclesonCurveLanes
F1 score· 2020-07-23
65.02
best: 88.47 (CondLSTR (ResNet-101))
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending arXiv:2007.12147
Autonomous VehiclesonCurveLanes
Precision· 2020-07-23
76.13
best: 93.58 (CurveLane-S)
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending arXiv:2007.12147
Autonomous VehiclesonCurveLanes
Recall· 2020-07-23
56.74
best: 84.36 (CANet-L(ResNet101))
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending arXiv:2007.12147

Computer Vision5 results

Lane DetectiononCurveLanes
GFLOPs· 2020-07-23
328.4
SOTA
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending arXiv:2007.12147
Lane DetectiononCULane
F1 score· uses extra data· 2017-12-17
71.6
best: 81.23 (DLNet)
SOTA
Spatial As Deep: Spatial CNN for Traffic Scene Understanding arXiv:1712.06080
Lane DetectiononCurveLanes
F1 score· 2020-07-23
65.02
best: 88.47 (CondLSTR (ResNet-101))
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending arXiv:2007.12147
Lane DetectiononCurveLanes
Precision· 2020-07-23
76.13
best: 93.58 (CurveLane-S)
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending arXiv:2007.12147
Lane DetectiononCurveLanes
Recall· 2020-07-23
56.74
best: 84.36 (CANet-L(ResNet101))
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending arXiv:2007.12147