Abstract: An embodiment provided herein preprocesses the input samples to the classification neural network, e.g., by adding Gaussian noise to word/sentence representations to make the function of the neural network satisfy Lipschitz property such that a small change in the input does not cause much change to the output if the input sample is in-distribution. Method to induce properties in the feature representation of neural network such that for out-of-distribution examples the feature representation magnitude is either close to zero or the feature representation is orthogonal to all class representations. Method to generate examples that are structurally similar to in-domain and semantically out-of domain for use in out-of-domain classification training. Method to prune feature representation dimension to mitigate long tail error of unused dimension in out-of-domain classification. Using these techniques, the accuracy of both in-domain and out-of-distribution identification can be improved.

Abstract: In some aspects, systems and methods for efficiently clustering a large-scale dataset for improving the construction and training of machine-learning models, such as neural network models, are provided. A dataset used for training a neural network model configured can be clustered into a first set of clusters and a second set of clusters. The neural network model can be constructed with a number of nodes in a hidden layer that is based on the number of clusters in the first set of clusters. The neural network can be trained based on training samples selected from the second set of clusters. In some aspects, the trained neural network model can be utilized to satisfy risk assessment queries to compute output risk indicators for target entities. The output risk indicator can be used to control access to one or more interactive computing environments by the target entities.

Abstract: A three-dimensional measurement apparatus determines, with respect to a captured image, a two-dimensional ranging path that is to undergo distance measurement; obtains, with respect to the captured image, distance information including information of subject distances of respective pixels in the captured image, the subject distances being distances to a subject; and derives a three-dimensional path length corresponding to the ranging path along a surface shape of the subject based on subject distances of respective pixels in the captured image that are included in the determined ranging path, and on information of an image capture condition of the captured image.

Abstract: Provided is a method for operating a robot, including capturing images of a workspace, comparing at least one object from the captured images to objects in an object dictionary, identifying a class to which the at least one object belongs using an object classification unit, instructing the robot to execute at least one action based on the object class identified, capturing movement data of the robot, and generating a planar representation of the workspace based on the captured images and the movement data, wherein the captured images indicate a position of the robot relative to objects within the workspace and the movement data indicates movement of the robot.

Abstract: A discrimination device includes a sub-data set extraction unit for extracting from a plurality of labeled learning data a sub-learning data set to be used for learning and a sub-verification data set to be used for verification, a learning unit for performing supervised learning on the basis of the sub-learning data set to generate a pre-trained model for discriminating a label from data related to an object, a discrimination unit for conducting a discrimination processing using the pre-trained model on each piece of learning data contained in the sub-verification data set, a verification result recording unit for recording a result of the discrimination processing in association with the learning data, and a correctness detection unit for detecting learning data attached with a label that may be incorrect based on the discrimination processing results recorded in association with respective learning data.

Abstract: Disclosed herein are a control server and method for controlling a robot using an artificial neural network, and a robot implementing the same. The robot includes a driver, a processor controlling the driver using an artificial neural network-based algorithm model, and a learning processor learning the algorithm model, where the algorithm model includes a first GAN (generative adversarial network) and a second GAN, the processor generates a plurality of real-like-fake images using a first generator included in a learned first GAN, the learning processor learns a second GAN based on a plurality of random texture rendered images and the plurality of real-like-fake images, and the processor generates a canonical image by inputting a real image to a second generator included in a learned second GAN, and controls the driver using the canonical image.

Abstract: A robot system, including: a robot; a base supporting the robot; a controller connected to the robot; a processor connected to the controller; a depth camera connected to the processor; a flange plate; a coupling shaft including a first end and a second end; a mounting base including an elongated hole, a first side wall, and a second side wall; a sprayer including a mounting shaft; a first positioning bolt; a limit arm includes a first end and a second end; an axis pin; a limit shaft; a second positioning bolt; a gas cylinder; a piston rod; a connector; a shifter level; a trigger. The robot is connected to the first end of the coupling shaft via the flange plate. The second end of the coupling shaft is connected to the mounting base. The mounting shaft of the sprayer is disposed in the elongated hole of the mounting base.

Abstract: A method for identifying objects for autonomous robots, including: capturing, with an image sensor disposed on an autonomous robot, images of a workspace, wherein a field of view of the image sensor captures at least an area in front of the autonomous robot; obtaining, with a processing unit disposed on the autonomous robot, the images; generating, with the processing unit, a feature vector from the images; comparing, with the processing unit, at least one object captured in the images to objects in an object dictionary; identifying, with the processing unit, a class to which the at least one object belongs; and executing, with the autonomous robot, instructions based on the class of the at least one object identified.

Abstract: Provided is a method for operating a robot, including capturing images of a workspace, comparing at least one object from the captured images to objects in an object dictionary, identifying a class to which the at least one object belongs using an object classification unit, instructing the robot to execute at least one action based on the object class identified, capturing movement data of the robot, and generating a planar representation of the workspace based on the captured images and the movement data, wherein the captured images indicate a position of the robot relative to objects within the workspace and the movement data indicates movement of the robot.

Abstract: A measurement apparatus comprising an acquisition memory adapted to store data sections of at least one acquired measurement signal; a processor adapted to calculate a measurement parameter vector, v, for each data section of the acquired measurement signal; and a trained autoencoder neural network adapted to process the measurement parameter vectors, v, applied as input data to the trained autoencoder neural network to provide at a middle layer of said autoencoder neural network an encoded vector, h, with characteristic signal features of the acquired measurement signal.

Abstract: To enable effectively narrowing down features to be generated, thereby generating effective features at a high speed, in obtaining the features from a large volume of data. A fixed rule and an additional rule are stored in advance. The fixed rule specifies a rule of a calculation operation for generating a new feature. The additional rule specifies whether to perform a calculation operation for generating the new feature on a basis of meta-information, not depending on whether the fixed rule is applicable. An objective variable is predicted from plurality of features on the basis of the fixed rule and the additional rule.

Abstract: An electronic device: obtains a plurality of sets of images; synthesizes a three-dimensional point cloud for each of the plurality of sets of images; constructs planes using the respective three-dimensional point clouds; and generates a merged set of quadtrees characterizing a merged set of planes across the three-dimensional point clouds.

Abstract: A method includes: generating a refine image having a maximized correct label score of inference from an incorrect image by which an incorrect label is inferred by a neural network; generating a third map by superimposing a first map and a second map, the first map indicating pixels to each of which a change is made in generating the refine image, of plural pixels of the incorrect image, the second map indicating a degree of attention for each local region in the refine image, the each local region being a region that has drawn attention at the time of inference by the neural network, and the third map indicating a degree of importance for each pixel for inferring a correct label; and specifying an image section based on a pixel value of the third map, the image section corresponding to a region causing incorrect inference in the incorrect image.

Abstract: Provided is a robot, including: a chassis; a set of wheels coupled to the chassis; a processor; and a tangible, non-transitory, machine-readable medium storing instructions that when executed by the processor effectuate operations including: capturing, by an image sensor disposed on a robot, images of a workspace; obtaining, by the processor of the robot or via the cloud, the captured images; comparing, by the processor of the robot or via the cloud, at least one object from the captured images to objects in an object dictionary; identifying, by the processor of the robot or via the cloud, a class to which the at least one object belongs using an object classification unit; and instructing, by the processor of the robot, the robot to execute at least one action based on the object class identified.

Abstract: A multi-label object detection method based on an object detection network includes: selecting an image of an object to be detected as an input image; based on a trained object detection network, obtaining a class of the object to be detected, coordinates of a center of the object to be detected, and a length and a width of a detection rectangular box according to the input image; and outputting the class of the object to be detected, the coordinates of the center of the object to be detected, and the length and the width of the detection rectangular box. The method of the present invention can perform real-time and accurate object detection on different classes of objects with improved detection speed and accuracy, and can solve the problem of object overlapping and occlusion during the object detection.

Abstract: Methods, systems, and computer-readable media for content moderation using object detection and image classification are disclosed. A content moderation system performs object detection on an input image using one or more object detectors. The object detection finds one or more elements in the input image. The content moderation system performs classification based at least in part on the input image using one or more image classifiers. The classification determines one or more values indicative of one or more content types in the input image. The content moderation system determines one or more scores for one or more content labels corresponding to the one or more content types. At least one of the scores represents a finding of one or more of the content types in the input image. The content moderation system generates output indicating the finding of the one or more of the content types.

Abstract: Techniques, devices, and systems to improve detection and security of a displayed image on a screen of a computer device, such as a device, including detection of an object in an environment, where the object has an inverse-colorspace relationship in relation to the colorspace of the environment. A system includes: a first camera device configured to determine a first underlying colorspace corresponding to an environment, a second camera device configured to determine a second underlying colorspace corresponding to either i) an actual change in the environment or ii) a predicted change in the environment, and a computer device configured to determine an inverse colorspace of at least one of i) the first underlying colorspace or ii) the second underlying colorspace and configured to detect an object in the environment based on the inverse colorspace determination.

Abstract: A system uses range and Doppler velocity measurements from a lidar system and images from a video system to estimate a six degree-of-freedom trajectory (6DOF) of a target. The 6DOF transformation parameters are used to transform multiple images to the frame time of a selected image, thus obtaining multiple images at the same frame time. These multiple images may be used to increase a resolution of the image at each frame time, obtaining the collection of the superresolution images.

Abstract: A search space for performing nearest neighbor searches for encoding point cloud data may be trimmed. Ranges of a space filling curve may be used to identify search space to exclude or reuse, instead of generating nearest neighbor search results for at least some of the points of a point cloud located within some of the ranges of the space filling curve. Additionally, neighboring voxels may be searched to identify any neighboring points missed during the trimmed search based on the ranges of the space filling curve.

Abstract: A machine learning apparatus that can quantitatively and accurately evaluate the state of a cable in a robot. A machine learning apparatus for learning a state of a cable mounted in a robot includes a learning data acquisition section that acquires, as a learning data set, image data of the cable captured by a camera while the robot performs a predetermined operation, and data representing a state of the cable while the robot performs the predetermined operation, and a learning section that generates a learning model representing a correlation between the image data and the state of the cable, using the learning data set.