You can submit your results on the test data using the form below.
Each researcher needs to evaluate his/her method on his/her own, because the labels for the test data were released. We ask every submission to be faithful in their test evaluation and to be in accordance with common research practices (e.g. no data leakage, no use of test data during training).
We take the liberty to remove or to not add submissions which seem to have violated the above condition.
“Trained on Car” all means that one model was trained on each vehicle. The general performance of the method was evaluated on the test set of each vehicle without the test performance of the vehicle it was trained on. Consequently, you calculated the mean of the means of the performances across all vehicles for the overall performance of the method.
If a single car is mentioned as the “Trained on Car”, then a single model was trained only on the mentioned car and the performance of this model on the test images of all unseen/unknown vehicles was evaluated. Consequently, you calculated the mean of the means of the performances across all vehicles without the test performance of the vehicle it was trained on.
The results will be added manually to the table, so it could take some time until the tables will be updated.