Deep face recognition based on clustering over unlabeled face data

A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method for implementing face recognition, the method performed by the computer comprising;

• obtaining a face recognition model trained on labeled face data;
• separating, using a mixture of probability distributions, a plurality of unlabeled faces corresponding to unlabeled face data into a set of one or more overlapping unlabeled faces that include overlapping identities to those in the labeled face data and a set of one or more disjoint unlabeled faces that include disjoint identities to those in the labeled face data;
• clustering the one or more disjoint unlabeled faces using a graph convolutional network to generate one or more cluster assignments, including assigning a pseudo-label corresponding to a cluster assignment to each of the one or more disjoint unlabeled faces to obtain one or more pseudo-labeled samples;
• generating a clustering uncertainty associated with the one or more cluster assignments;
• and
• retraining the face recognition model on the labeled face data and the unlabeled face data to improve face recognition performance by incorporating the clustering uncertainty;
• wherein retraining the face recognition model further includes:
• feeding the labeled face data and the one or more pseudo-labeled samples into a neural network;
• and
• attenuating a training loss of the one or more pseudo-labeled samples by using the clustering uncertainty and an output of the neural network to obtain a weighted training loss.

A system for implementing face recognition, comprising:

• a memory device storing program code;
• and
• at least one processor device operatively coupled to the memory device and configured to execute program code stored on the memory device to:
• obtain a face recognition model trained on labeled face data;
• separate, using a mixture of probability distributions, a plurality of unlabeled faces corresponding to unlabeled face data into a set of one or more overlapping unlabeled faces that include overlapping identities to those in the labeled face data and a set of one or more disjoint unlabeled faces that include disjoint identities to those in the labeled face data;
• cluster the one or more disjoint unlabeled faces using a graph convolutional network to generate one or more cluster assignments by assigning a pseudo-label corresponding to a cluster assignment to each of the one or more disjoint unlabeled faces to obtain one or more pseudo-labeled samples;
• generate a clustering uncertainty associated with the one or more cluster assignments;
• and
• retrain the face recognition model on the labeled face data and the unlabeled face data to improve face recognition performance by incorporating the clustering uncertainty;
• wherein the at least one processor device is further configured to retrain the face recognition model by;
• feeding the labeled face data and the one or more pseudo-labeled samples into a neural network;
• and
• attenuating a training loss of the one or more pseudo-labeled samples by using the clustering uncertainty and an output of the neural network to obtain a weighted training loss.