Abstract: A content analyzer determines whether various types of modification have been made to images. The content analyzer computes JPEG ghosts from the images that are concatenated with the image channels to generate a feature vector. The feature vector is provided as input to a neural network that determines whether the types of modification have been made to the image. The neural network may include a constrained convolution layer and several unconstrained convolution layers. An image fake model may also be applied to determine whether the image was generated using a computer model or algorithm.

Abstract: In one embodiment, a method includes accessing a first machine-learning model trained to generate a feature representation of an input data, a second machine-learning model trained to generate a desired result based on the feature representation, and a third machine-learning model trained to generate an undesired result based on the feature representation, and training a fourth machine-learning model by generating a secured feature representation by processing a first output of the first machine-learning model using the fourth machine-learning model, generating a second output and a third output by processing the secured feature representation using, respectively, the second and third machine-learning models, and updating the fourth machine-learning model according to an optimization function configured to optimize a correctness of the second output and an incorrectness of the third output.

Abstract: Systems, methods, and non-transitory computer-readable media can be configured to train a featurizer based at least in part on a set of training data. The featurizer can be applied to at least one input to generate at least one tensor. The at least one tensor obfuscates or excludes at least one feature in the at least one input.

Abstract: A content analyzer determines whether various types of modification have been made to images. The content analyzer computes JPEG ghosts from the images that are concatenated with the image channels to generate a feature vector. The feature vector is provided as input to a neural network that determines whether the types of modification have been made to the image. The neural network may include a constrained convolution layer and several unconstrained convolution layers. An image fake model may also be applied to determine whether the image was generated using a computer model or algorithm.

Abstract: In one embodiment, a computing system may access a training image and a reference image of a person and an incomplete image. A generate may generate an in-painted image based on the incomplete image, and a discriminator may be used to determine whether each of the in-painted image, the training image, and the reference image is likely generated by the generator. The system may compute losses based on the determinations and update the discriminator accordingly. Using the updated discriminator, the system may determine whether a second in-painted image generated by the generator is likely generated by the generator. The system may compute a loss based on the determination and update the generator accordingly. Once training is complete, the generator may be used to generate a modified version of a given image, such as making the eyes of a person appear open even if they were closed in the input image.

Abstract: In one embodiment, a computing system may access a training image and a reference image of a person and an incomplete image. A generate may generate an in-painted image based on the incomplete image, and a discriminator may be used to determine whether each of the in-painted image, the training image, and the reference image is likely generated by the generator. The system may compute losses based on the determinations and update the discriminator accordingly. Using the updated discriminator, the system may determine whether a second in-painted image generated by the generator is likely generated by the generator. The system may compute a loss based on the determination and update the generator accordingly. Once training is complete, the generator may be used to generate a modified version of a given image, such as making the eyes of a person appear open even if they were closed in the input image.

Abstract: Examples are disclosed herein that relate to face detection. One example provides a computing device comprising a logic subsystem and a storage subsystem holding instructions executable by the logic subsystem to receive an image, apply a tile array to the image, the tile array comprising a plurality of tiles, and perform face detection on at least a subset of the tiles, where determining whether or not to perform face detection on a given tile is based on a likelihood that the tile includes at least a portion of a human face.

Abstract: In a face recognition system, a face classifier is configured to receive an input image, and analyze the input image to determine at least one specific trait. A feature extractor is configured to receive a plurality of data sets based on the determined specific trait, and generate a plurality of feature sets corresponding to the plurality of data sets, wherein respective ones of the feature sets include corresponding features extracted from respective ones of the data sets. A feature comparator is configured to receive a plurality of images from an image database, compare the input image against the plurality of images from the image database by using the plurality of feature sets generated by the feature extractor, and output a ranking of potential matches indicating a likelihood of a match between the input image and the plurality of images in the image database.

Abstract: An active rangefinder system disclosed herein parameterizes a set of transformations predicting different possible appearances of a projection feature projected into a three-dimensional scene. A matching module matches an image of the projected projection feature with one of the transformations, and a depth estimation module estimates a distance to an object reflecting the projection feature based on the transformation identified by the matching module.