An example system includes a processor to receive detections or recognitions with confidence scores for an object in a medium from a plurality of trained detection or recognition models. The processor is to generate a probability of correctness for each of the detections or recognitions based on the confidence scores via correctness mappings generated for each of the trained detection or recognition models. The processor is to also select a detection or recognition with a higher probability of correctness from the detections or recognitions. The processor is to perform a detection or recognition task based on the selected detection or recognition.