Deep face recognition based on clustering over unlabeled face data

1. Computer-implemented method for implementing face recognition, 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 b using the clustering uncertainty and an output of the neural network to obtain a weighted training loss.

2. The method as recited in claim 1 , wherein the deep neural network is trained on labeled faces in a fully-supervised fashion.

3. The method as recited in claim 1 , wherein the mixture of probability distributions includes a mixture of Weibull distributions.

4. The method as recited in claim 1 , wherein obtaining the estimated clustering uncertainty further includes learning an unsupervised model of a likelihood of incorrect cluster assignments.

5. The method as recited in claim 1 , further comprising implementing the face recognition model to perform a face recognition task.

6. The method as recited in claim 5 , wherein the face recognition model is implemented within a biometric system that provides a user access to a computing system or device based on an analysis of the user's face.

7. 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.

8. The computer program product as recited in claim 7 , wherein the deep neural networks is trained on labeled faces in a fully-supervised fashion.

9. The computer program product as recited in claim 7 , wherein the mixture of probability distributions includes a mixture of Weibull distributions.

10. The computer program product as recited in claim 7 , wherein obtaining the estimated clustering uncertainty further includes learning an unsupervised model of a likelihood of incorrect cluster assignments.

11. The computer program product as recited in claim 7 , wherein the method further includes implementing the face recognition model to perform a face recognition task.

12. The computer program product as recited in claim 11 , wherein the face recognition model is implemented within a biometric system that provides a user access to a computing system or device based on an analysis of the user's face.

13. 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.

14. The system as recited in claim 13 , wherein the deep neural network trained on labeled faces in a fully-supervised fashion.

15. The system as recited in claim 11 , wherein of probability distributions includes a mixture of Weibull distributions.

16. The system as recited in claim 13 , Wherein the at least one processor device is further configured to generate the clustering uncertainty by learning an unsupervised model of a likelihood of incorrect cluster assignments.

17. The system as recited in claim 13 , Wherein the at least one processor device is further configured to execute program code stored on the memory device to implement the face recognition model to perform a face recognition task, and wherein the face recognition model is implemented within a biometric system that provides a user access to a computing system or device based on an analysis of the user's face.