A computer-implemented method for generating unified soft labels is disclosed. In the computer-implemented method, a collection of samples is prepared. Then, a plurality of predictions generated by a plurality of individual trained models is obtained for each sample, in which each individual trained model has an individual class set to form at least partially a unified class set that includes a plurality of target classes. The unified soft labels are estimated for each sample over the target classes in the unified class set from the plurality of the predictions using a relation connecting a first output of each Individual trained model and a second output of the unified model. The unified soft labels are output to train a unified model having the unified class set.
展开▼
