US 10,650,276 B1 · Learning to process images depicting faces without leveraging sensitive attributes in deep learning models

Abstract

Systems, methods, and articles of manufacture to generate, by a neural network of a variational autoencoder, a latent vector for a first input image, generate, by the neural network of the variational autoencoder, a first reconstructed image by sampling the latent vector for the first input image, determine a reconstruction loss incurred in generating the first reconstructed image based at least in part on: (i) a difference of the first input image and the first reconstructed image, and (ii) a master model trained to detect a sensitive attribute in images, determine a total loss based at least in part on the reconstruction loss and a classification loss, and optimize a plurality of weights of the neural network of the variational autoencoder based on a backpropagation operation and the determined total loss, the optimized neural network trained to not consider the sensitive attribute in images.

Claims20

Dependent claims

A system, comprising:

a processor circuit;
and
a memory storing instructions which when executed by the processor circuit cause the processor circuit to:
generate, by a neural network of a variational autoencoder, a latent vector for a first input image, a plurality of weights of the neural network optimized during training to not consider a sensitive attribute in images, the neural network trained based on:
(i) a master model trained to detect the sensitive attribute in images, and (ii) a reconstruction loss in generating reconstructed training images, the reconstruction loss based on a difference between a training image and the reconstructed training image;
generate, by the neural network, a first reconstructed image by sampling the latent vector for the first input image;
and
perform an image processing operation on the first reconstructed image.

5 more elements

A non-transitory computer-readable storage medium storing instructions that when executed by a processor cause the processor to:

generate, by a neural network of a variational autoencoder, a latent vector for a first input image, a plurality of weights of the neural network optimized during training to not consider a sensitive attribute in images, the neural network trained based on:
(i) a master model trained to detect the sensitive attribute in images, and (ii) a reconstruction loss in generating reconstructed training images, the reconstruction loss based on a difference between a training image and the reconstructed training image;
generate, by the neural network, a first reconstructed image by sampling the latent vector for the first input image;
and
perform an image processing operation on the first reconstructed image.

2 more elements

A method, comprising:

generating, by a neural network of a variational autoencoder, a latent vector for a first input image, a plurality of weights of the neural network optimized during training to not consider a sensitive attribute in images, the neural network trained based on:
(i) a master model trained to detect the sensitive attribute in images, and (ii) a reconstruction loss in generating reconstructed training images, the reconstruction loss based on a difference between a training image and the reconstructed training image;
generating, by the neural network, a first reconstructed image by sampling the latent vector for the first input image;
and
performing an image processing operation on the first reconstructed image.

2 more elements

Dependencies are inferred from the claim text.

Learning to process images depicting faces without leveraging sensitive attributes in deep learning models

Life of this patent

Learning to process images depicting faces without leveraging sensitive attributes in deep learning models

Life of this patent

Abstract

Claims20