Loading patent…
AssigneeApple Inc.
InventorsRahul Raguram, Vivek Roy, Shashank Tyagi, Huy Tho Ho, Kjell Fredrik Larsson
Estimating the term…
Techniques are disclosed for training a feature extraction model. A computing device can receive a training image and generate noised feature vectors using a feature extraction model characterized by first parameters and taking the training image as input. The computing device can determine the noised feature vectors by at least determining a feature vector for individual pixels in the training image and applying noise to each feature vector. The computing device can generate a reconstructed image using a reconstructor model characterized by second parameters and taking the noised feature vectors as input. The computing device can determine a reconstruction loss by comparing the training image with the reconstructed image and a noise loss using the noise applied to each feature vector. The computing device can update the first parameters based on the noise loss.
A computer-implemented method, comprising:
A system, comprising:
One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to at least:
The system of claim 10, wherein updating the first parameters comprises updating the first parameters to minimize the noise loss.
The system of claim 10, further comprising updating the second parameters based on the reconstruction loss.
The system of claim 10, wherein determining a reconstruction loss comprises computing a similarity measure between the training image and the reconstructed image.
The system of claim 10, wherein the feature vector comprises a plurality of feature values encoding information associated with the pixel corresponding to the feature vector, and wherein applying the noise to each feature vector comprises perturbing one or more of the plurality of feature values.
The one or more non-transitory computer-readable media of claim 16, wherein the feature extraction model comprises a noiser network characterized by at least one of the of the first parameters.
The one or more non-transitory computer-readable media of claim 16, wherein the training image comprises an identifiable element.
The one or more non-transitory computer-readable media of claim 16, wherein determining a reconstruction loss comprises computing a similarity measure between the training image and the reconstructed image.
Dependencies are inferred from the claim text.