One embodiment facilitates generating synthetic data objects using a semi-supervised GAN. During operation, a generator module synthesizes a data object derived from a noise vector and an attribute label. The system passes, to an unsupervised discriminator module, the data object and a set of training objects which are obtained from a training data set. The unsupervised discriminator module calculates: a value indicating a probability that the data object is real; and a latent feature representation of the data object. The system passes the latent feature representation and the attribute label to a supervised discriminator module. The supervised discriminator module calculates a value indicating a probability that the attribute label given the data object is real. The system performs the aforementioned steps iteratively until the generator module produces data objects with a given attribute label which the unsupervised and supervised discriminator modules can no longer identify as fake.

The present application discloses an image element matching method and apparatus, a model training method and apparatus, and a data processing method. The issue of finding image information matching a given image element is converted into the issue of predicting, from a matching knowledge graph, whether or not an edge is present between a node corresponding to the given image element and another node in the matching knowledge graph. Therefore, matching between image elements is flexibly implemented, matching performance is improved, and labor costs are reduced.

An inference system performs inference, such as object recognition, based on sensory inputs generated by sensors and control information associated with the sensory inputs. The sensory inputs describe one or more features of the objects. The control information describes movement of the sensors or known locations of the sensors relative to a reference point. For a particular object, an inference system learns a set of object-location representations of the object. An object-location representation is a unique characterization of an object-centric location relative to the particular object. The inference system also learns a set of feature-location representations associated with the object-location representation that indicate presence of features at the corresponding object-location pair. The inference system can perform inference on an unknown object by identifying candidate object-location representations consistent with feature-location representations observed from the sensory input data and control information.

The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

A processor-implemented method of generating feature data includes: receiving an input image; generating, based on a pixel value of the input image, at least one low-bit image having a number of bits per pixel lower than a number of bits per pixel of the input image; and generating, using at least one neural network, feature data corresponding to the input image from the at least one low-bit image.

A quantification system (700) is described that includes: at least one input (710) configured to provide two input medical images and two locations of interest in said input medical images that correspond to a same anatomical region; and a mapping circuit (725) configured to compute a direct quantification of change of said input medical images from the at least one input (710).

The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

A plant treatment platform uses a plant detection model to detect plants as the plant treatment platform travels through a field. The plant treatment platform receives image data from a camera that captures images of plants (e.g., crops or weeds) growing in the field. The plant treatment platform applies pre-processing functions to the image data to prepare the image data for processing by the plant detection model. For example, the plant treatment platform may reformat the image data, adjust the resolution or aspect ratio, or crop the image data. The plant treatment platform applies the plant detection model to the pre-processed image data to generate bounding boxes for the plants. The plant treatment platform then can apply treatment to the plants based on the output of the machine-learned model.

The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.