Abstract:
An apparatus and method with out-of-distribution data detection is provided. The apparatus includes one or more processors configured to execute instructions; and one or more memories storing the instructions, wherein, the execution of the instructions by the one or more processors configures the one or more processors to generate output data using a neural network model provided input data; determine, based on the output data, a maximum loss value among calculated loss values that correspond to neighboring data within a reference distance from the input data; and detect, based on the maximum loss value and a threshold, whether the input data is out-of-distribution (OOD) data that is different from in-distribution data corresponding to training data used in a training of the neural network model.
Abstract:
Example embodiments disclose a fingerprint recognition sensor and a fingerprint recognition system. The fingerprint recognition sensor may include a pad configured to apply a first wave signal having multi-frequency characteristics to an object, a signal applying electrode configured to transmit the first wave signal having multi-frequency characteristics to the pad and a signal receiving electrode configured to receive a reflection wave signal from the object to the pad based on the first wave signal.
Abstract:
A method of searching for hyperparameters for neural network learning includes: obtaining a preset early stop point; determining whether a current trial, among trials for searching for different combinations of hyperparameters, corresponds to a dry run trial; in response to a determination that the current trial corresponds to a dry run trial: executing learning epochs belonging to the current trial; searching for a combination of hyperparameters assigned to the current trial according to a result of the executing of the learning epochs; and changing the early stop point by based on whether an early stop with respect to a found combination of the hyperparameters is a success in each of the learning epochs.
Abstract:
A method of a system including a processor including recording experiment information of a job in connection with job information generated based on an execution of a job of a computer cluster system, and controlling further execution of a job, by the computer cluster system, by transmitting a change in the experiment information to the computer cluster system based on the job information.
Abstract:
An image processing method includes receiving an input image and a guide image corresponding to the input image, extracting informative features from the input image and the guide image to enhance the input image, selectively obtaining a first feature for the input image from among the informative features, and processing the input image based on the first feature.
Abstract:
Provided is a vehicle radar apparatus for providing three-dimensional (3D) information about an environment. The vehicle radar apparatus may include a transmitter configured to transmit electromagnetic waves, a receiver configured to receive reflected electromagnetic waves, and a signal processor configured to extract 3D information about the environment based on the reflected electromagnetic waves. The transmitter may transmit electromagnetic waves to the environment by performing a two-dimensional (2D) scan, and the receiver may receive the reflected electromagnetic waves by performing a one-dimensional (1D) scan. Alternatively, the transmitter may transmit the electromagnetic waves to the environment by performing a 1D scan, and the receiver may receive the reflected electromagnetic waves by performing a 2D scan.
Abstract:
A method and apparatus for classifying a text using a text classification model are disclosed. In one general aspect, an apparatus is for outputting a classification result for an input text including words by using a text classification model, and the apparatus includes: one or more processors; a memory including instructions configured to cause the one or more processors to: determine whether the input text indicates an anomaly; and responsive to determining that the input text indicates an anomaly: determine saliencies of the respective words; select target words from among the words based on the saliencies; generate a replaced text by replacing, in the input text, the selected words with other words; and obtain a text classification result of the input text based on an inference upon the replaced text by the text classification model receiving the replaced text as an input.
Abstract:
An image processing method includes receiving an input image and a guide image corresponding to the input image, extracting informative features from the input image and the guide image to enhance the input image, selectively obtaining a first feature for the input image from among the informative features, and processing the input image based on the first feature.
Abstract:
Provided is a fingerprint authentication system and a method of authentication. The fingerprint authentication system may have a configuration to analyze a reflection wave signal reflected at a surface of an object under examination or an internal of the object under examination by applying a wave signal from at least one of signal communication unit of a fingerprint sensor to the object under examination. In the method of authentication, the controller in the fingerprint authentication system may be configured to selectively perform a first step authentication to authenticate a shape of a fingerprint, and a second step authentication to detect internal biometric information of the object under examination.
Abstract:
A mobile device which senses particulate matter is provided. The mobile device includes a housing having an air flow path through which air flows when the mobile device is shaken; an inertia sensor that detects acceleration of the mobile device; a light-scattering type sensor that irradiates the air flow path with light and detects particulate matter in air flowing through the air flow path; and a controller that includes a counter for counting the particulate matter detected by the light-scattering type sensor, and a flow rate calculator for detecting an air flow rate of the air flow path based on a detection signal of the inertia sensor.