Methods, systems, and devices for training and verification of learning models are described. A device may capture a camera frame including a road feature of a physical environment, determine a first classification and a first localization of the road feature based on positioning information of the road feature from a high-definition map and positioning information of the device from a positioning engine. The device may analyze a learning model by comparing one or more of the first classification of the road feature or the first localization of the road feature in the camera frame to one or more of a second classification or a second localization of the road feature determined by the learning model. The device may then determine a loss comparison value and adapt the learning model according to the loss comparison value.