Horizon Line Estimation on HLW (held)
65.73AUC (theta, rho)Places
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PlacesLearning Paradigm=Classification, Loss Function=Softmax, Initialization=Places2016.04 | 65.73 | 59.54 | |
| SalientLearning Paradigm=Classification, Loss Function=Softmax, Initialization=Salient2016.04 | 64.65 | 62.1 | |
| ImageNetLearning Paradigm=Classification, Loss Function=Softmax, Initialization=ImageNet2016.04 | 64.49 | 62.1 | |
| Best (Regression Huber)Learning Paradigm=Regression, Loss Function=Huber, Initialization=Best Classification Network2016.04 | 62.86 | 63.23 | |
| RandomLearning Paradigm=Classification, Loss Function=Softmax, Initialization=Random2016.04 | 62.27 | 56.64 | |
| PoseNetLearning Paradigm=Classification, Loss Function=Softmax, Initialization=PoseNet2016.04 | 60.49 | 61.35 | |
| Best (Regularized Huber)Learning Paradigm=Regression (regularized w/ classification), Loss Function=Huber, Initialization=Best Classification Network2016.04 | 60.38 | 60.51 | |
| Zhai et al.2016.04 | 57.33 | — | |
| Best (Regularized L2)Learning Paradigm=Regression (regularized w/ classification), Loss Function=L2, Initialization=Best Classification Network2016.04 | 57.29 | 58.48 | |
| Best (Regression)Learning Paradigm=Regression, Loss Function=L2, Initialization=Best Classification Network2016.04 | 55.54 | 56.55 | |
| Places (Regression Huber)Learning Paradigm=Regression, Loss Function=Huber, Initialization=Places2016.04 | 53.11 | 53.85 | |
| Lezama et al.2016.04 | 51.32 | — | |
| Places (Regression)Learning Paradigm=Regression, Loss Function=L2, Initialization=Places2016.04 | 44.54 | 45.86 |