L2 constrained softmax loss for discriminative face verification
AssigneeUniversity of Maryland, College Park
InventorsRajeev Ranjan, Carlos Castillo, Ramalingam Chellappa
Life of this patent
Estimating the term…
Abstract
Various face discrimination systems may benefit from techniques for providing increased accuracy. For example, certain discriminative face verification systems can benefit from L2-constrained softmax loss. A method can include applying an image of a face as an input to a deep convolutional neural network. The method can also include applying an output of a fully connected layer of the deep convolutional neural network to an L2-normalizing layer. The method can further include determining softmax loss based on an output of the L2-normalizing layer.
Claims12
A method, comprising:
- applying an image of a face as an input to a deep convolutional neural network;
- applying an output of a fully connected layer of the deep convolutional neural network to an L2-normalizing layer;
- determining softmax loss based on an output of the L2-normalizing layer;
- and
- applying an output of the L2-normalizing layer to a scale layer.
A training network comprising:
- an input configured to receive an image of a face;
- a deep convolutional neural network configured to train based on the image, and including a fully connected layer at an output of the deep convolutional neural network;
- an L2-normalizing layer at an output of the fully connected layer;
- and
- a scale layer at an output of the L2-normalizing layer.
A testing neural network, comprising:
- a deep convolutional neural network trained according to a process, the process comprising
- applying an output of a fully connected layer of the deep convolutional neural network to an L2-normalizing layer;
- determining softmax loss based on an output of the L2-normalizing layer;
- applying an output of the L2-normalizing layer to a scale layer.
Dependencies are inferred from the claim text.