Baseline comparison

[a1wj1]

May I ask if these experimental results were directly run from the training weight files of other papers? Or would you like to retrain using the data you collected？

[deepcs233]

Hi! Most of them have reported the corrsponding results in these benchmarks, we just copy them to here. We retrain the others models with the data we collected. Because different benchmarks use different data split (town, weather, etc.)