Hi, I have some confusion about the versions of the mapillary dataset.
In the paper you claim you have used 35 foreground classes of the mapillary dataset. However, this should correspond to v1.2 according to official instructions.
The Mapillary Vistas Dataset is a large-scale street-level image dataset containing 25,000 high-resolution images annotated into 66/124 object categories of which 37/70 classes are instance-specific labels (v.1.2 and v2.0, respectively).
Hi, I have some confusion about the versions of the mapillary dataset.