Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network system used to control an agent interacting with an environment to perform a specified task. One of the methods includes causing the agent to perform a task episode in which the agent attempts to perform the specified task; for each of one or more particular time steps in the sequence: generating a modified reward for the particular time step from (i) the actual reward at the time step and (ii) value predictions at one or more time steps that are more than a threshold number of time steps after the particular time step in the sequence; and training, through reinforcement learning, the neural network system using at least the modified rewards for the particular time steps.

A computer implemented method of generating at least one shape of a region of interest in a digital image is provided. The method includes obtaining, by an image processing engine, access to a digital tissue image of a biological sample; tiling, by the image processing engine, the digital tissue image into a collection of image patches; identifying, by the image processing engine, a set of target tissue patches from the collection of image patches as a function of pixel content within the collection of image patches; assigning, by the image processing engine, each target tissue patch of the set of target tissue patches an initial class probability score indicating a probability that the target tissue patch falls within a class of interest, the initial class probability score generated by a trained classifier executed on each target tissue patch; generating, by the image processing engine, a first set of tissue region seed patches by identifying target tissue patches having initial class probability scores that satisfy a first seed region criteria, the first set of tissue region seed patches comprising a subset of the set of target tissue patches; generating, by the image processing engine, a second set of tissue region seed patches by identifying target tissue patches having initial class probability scores that satisfy a second seed region criteria, the second set of tissue region seed patches comprising a subset of the set of target tissue patches; calculating, by the image processing engine, a region of interest score for each patch in the second set of tissue region seed patches as a function of initial class probability scores of neighboring patches of the second set of tissue region seed patches and a distance to patches within the first set of issue region seed patches; and generating, by the image processing engine, one or more region of interest shapes by grouping neighboring patches based on their region of interest scores.

Before dimension reduction is performed while local data distribution is stored as neighborhood data, a distance between data to be subjected to the dimension reduction is calculated, and a parameter (a neighborhood number of the k-nearest neighbor algorithm or a size of a hypersphere) which determines the neighborhood data is determined for each data to be subjected to the dimension reduction. Thereafter, the dimension reduction is performed on the target data based on the determined parameter.

Vehicle perception techniques include obtaining a training dataset represented by N training histograms, in an image feature space, corresponding to N training images, K-means clustering the N training histograms to determine K clusters with respective K respective cluster centers, wherein K and N are integers greater than or equal to one and K is less than or equal to N, comparing the N training histograms to their respective K cluster centers to determine maximum in-class distances for each of K clusters, applying a deep neural network (DNN) to input images of the set of inputs to output detected/classified objects with respective confidence scores, obtaining adjusted confidence scores by adjusting the confidence scores output by the DNN based on distance ratios of (i) minimal distances of input histograms representing the input images to the K cluster centers and (ii) the respective maximum in-class.

A method of sampling and decoding of a signal of interest x comprising, at a training stage: acquiring a set of training signals {x.sub.i}.sub.i=1.sup.M, providing a sampling operator P.sub. and a decoder g.sub.g(.), training operator P.sub. on signals {x.sub.i}.sub.i=1.sup.M to obtain a learned sampling operator P.sub.{circumflex over ()}; and, at a sampling stage: applying P.sub.{circumflex over ()} in a transform domain If to signal x, resulting in observation signal y; applying the decoder g.sub.g(.) to y, to produce an estimate {circumflex over (x)} of signal x to decode and/or, decide about, the signal. Decoder g.sub.g(.) is trained jointly with P.sub. on signals {x.sub.i}.sub.i=1.sup.M, to obtain a learned decoder g.sub.g, by jointly determining, during a cost minimization step, sampling parameters and decoding parameters .sub.gaccording to a cost function, and wherein the step of applying the decoder g.sub.g(.) uses decoding parameters .sub.g, such that estimate {circumflex over (x)} is produced by the learned decoder g.sub.{circumflex over ()}g.

An image recognition method includes: selecting an augmentation process from augmentation processes based on a probability table, in response to an acquisition of an input image; acquiring an augmented image by augmenting the input image based on the selected augmentation process; and recognizing an object from the augmented image based on a recognition model.

A method for user authentication based on feature information includes: judging whether a user to be authenticated belongs to a similar user group, wherein the similar user group comprises at least two similar users, and the similar users are users whose reference feature information meets a preset similarity condition and a preset distinguishability condition; and authenticating the user to be authenticated according to reference feature information in the similar user group if the user to be authenticated belongs to the similar user group.

A system for image classification is disclosed that includes a central system configured to provide high reliability image data processing and recognition and a plurality of endpoint systems, each configured to provide image data processing and recognition with a lower reliability than the central system and to generate probability data. A decision switch disposed at each of the plurality of endpoint systems is configured to receive the probability data and to determine whether to deny access, grant access or generate a referral message to the central system, wherein the referral message includes at least a set of image data generated at the endpoint system.

An object feature extraction device according to an aspect of the present invention includes: at least one memory storing instructions; and at least one processor configured to execute the instructions to: detect an object from an image, and generate area information indicating an area where the object is present, and resolution information pertaining to resolution of the object; and extract, from the image within an area defined by the area information, a feature indicating a feature of the object in consideration of the resolution information.

An image processing apparatus for reducing an influence of a false detection from processing for detecting a predetermined object, and a control method thereof are provided. An image processing apparatus, comprising: a detecting unit for detecting a region of a predetermined object from an image; a determining unit for determining whether the detection by the detecting unit is a false detection; a processing unit for performing processing relating to the predetermined object on the region detected by the detecting unit; and a controlling unit for controlling, based on a determination result by the determining unit, execution of the processing by the processing unit on the region detected by the detecting unit.