Long-tail large scale face recognition by non-linear feature level domain adaptation
A computer-implemented method, system, and computer program product are provided for facial recognition. The method includes receiving, by a processor device, a plurality of images. The method also includes extracting, by the processor device with a feature extractor utilizing a convolutional neural network (CNN) with an enlarged intra-class variance of long-tail classes, feature vectors for each of the plurality of images. The method additionally includes generating, by the processor device with a feature generator, discriminative feature vectors for each of the feature vectors. The method further includes classifying, by the processor device utilizing a fully connected classifier, an identity from the discriminative feature vector. The method also includes control an operation of a processor-based machine to react in accordance with the identity.
1. A mobile device with facial recognition, the mobile device comprising:
one or more cameras;
a processor device and memory coupled to the processor device, the processing system programmed to:
receive a plurality of images from the one or more cameras;
extract, with a feature extractor utilizing a convolutional neural network (CNN) with an enlarged intra-class variance of long-tail classes, feature vectors from each of the plurality of images;
generate, with a feature generator, discriminative feature vectors for each of the feature vectors;
classify, with a fully connected classifier, an identity from the discriminative feature vectors; and
control an operation of the mobile device to react in accordance with the identity.
2. The mobile device as recited in claim 1 , further includes a communication system.
3. The mobile device as recited in claim 1 , wherein the operation tags the video with the identity and uploads the video to social media.
4. The mobile device as recited in claim 1 , wherein the operation tags the video with the identity and sends the video to a user.
5. The mobile device as recited in claim 1 , wherein the mobile device is a smart phone.
6. The mobile device as recited in claim 1 , wherein the mobile device is a body cam.
7. The mobile device as recited in claim 1 , further programmed to train the feature extractor, the feature generator, and the fully connected classifier with an alternative bi-stage strategy.
8. The mobile device as recited in claim 1 , wherein the feature extractor shares covariance matrices across all classes to transfer intra-class variance from regular classes to the long-tail classes.
9. The mobile device as recited in claim 1 , wherein the feature generator optimizes a softmax loss by joint regularization of weights and features through a magnitude of an inner product of the weights and features.
10. The mobile device as recited in claim 1 , wherein the feature extractor averages the feature vector with a flipped feature vector, the flipped feature vector being generated from a horizontally flipped frame from one of the plurality of images.
11. The mobile device as recited in claim 1 , wherein each of the plurality of images is selected from the group consisting of an image, a video, and a frame from the video.
12. The mobile device as recited in claim 2 , wherein the communication system connects to a remote server that includes a facial recognition network.
13. The mobile device as recited in claim 7 , wherein one stage of the alternative bi-stage strategy fixes the feature extractor and applies the feature generator to generate new transferred features that are more diverse and violate a decision boundary.
14. The mobile device as recited in claim 7 , wherein one stage of the alternative bi-stage strategy fixes the fully connected classifier and updates the feature extractor and the feature generator.
15. A computer program product for a mobile device with facial recognition, the 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 comprising:
receiving, by a processor device, a plurality of images;
extracting, by the processor device with a feature extractor utilizing a convolutional neural network (CNN) with an enlarged intra-class variance of long-tail classes, feature vectors for each of the plurality of images;
generating, by the processor device with a feature generator, discriminative feature vectors for each of the feature vectors;
classifying, by the processor device utilizing a fully connected classifier, an identity from the discriminative feature vector; and
controlling an operation of the mobile device to react in accordance with the identity.
16. A computer-implemented method for facial recognition in a mobile device, the method comprising:
receiving, by a processor device, a plurality of images;
extracting, by the processor device with a feature extractor utilizing a convolutional neural network (CNN) with an enlarged intra-class variance of long-tail classes, feature vectors for each of the plurality of images;
generating, by the processor device with a feature generator, discriminative feature vectors for each of the feature vectors;
classifying, by the processor device utilizing a fully connected classifier, an identity from the discriminative feature vector; and
controlling an operation of the mobile device to react in accordance with the identity.
17. The computer-implemented method as recited in claim 16 , wherein controlling includes tagging the video with the identity and uploading the video to social media.
18. The computer-implemented method as recited in claim 16 , wherein controlling includes tagging the video with the identity and sending the video to a user.
19. The computer-implemented method as recited in claim 16 , wherein extracting includes sharing covariance matrices across all classes to transfer intra-class variance from regular classes to the long-tail classes.