manot

About manot

manot monitors computer vision models' performance detecting discrepancies between training data and the real world. manot allows companies that use computer vision systems to monitor the performance of their models in the real world. While observing the model’s performance, manot first identifies the instances where the model is likely to fail. Then, it provides the option to filter those samples out so that they can be correctly labeled and introduced into the models' training dataset. Manot also determines whether or not the discrepancy that it has detected is a false positive or false negative, which allows the user to make a better-informed decision as to what to do with the detected anomaly.