License plate recognition (“LPR”) systems may encounter degradation in quality and obstructions that negatively impact performance of the LPR systems. A LPR system is configured to apply image processing algorithms to output information describing performance of the system and to monitor the performance of the system over time. Based on the performance of the system over time, the LPR system determines when one or more entities of the system require action to maintain or improve performance and transmits information describing the required action.

Disclosed is an apparatus and method with object detection. The method may include updating a pre-trained model based on sensing data of an image sensor, performing pseudo labeling using an interim model provided a respective training set, determining plural confidence thresholds based on an evaluation of the interim model, performing multiple trainings using the interim model and the generated pseudo labeled data, by applying the determined plural confidence thresholds to the multiple trainings, respectively, and generating an object detection model dependent on the performance of the multiple trainings, including generating an initial candidate object detection model when the interim model is the updated model.

An electronic apparatus is provided. The electronic apparatus includes: a memory storing a trained model including a plurality of layers; and a processor initializing a parameter matrix and a plurality of split variables of a trained model, calculating a new parameter matrix having a block-diagonal matrix for the plurality of split variables and the trained model to minimize a loss function for the trained model, a weight decay regularization term, and an objective function including a split regularization term defined by the parameter matrix and the plurality of split variables, vertically splitting the plurality of layers according to the group based on the computed split parameters and reconstruct the trained model using the computed new parameter matrix as parameters of the vertically split layers.

This disclosure relates to improved sketch-based image retrieval (SBIR) techniques. The SBIR techniques utilize a neural network architecture to train a domain migration function and a hashing function. The domain migration function is configured to transform sketches into synthetic images, and the hashing function is configured to generate hash codes from synthetic images and authentic images in a manner that preserves semantic consistency across the sketch and image domains. The hash codes generated from the synthetic images can be used for accurately identifying and retrieving authentic images corresponding to sketch queries, or vice versa.

The present teaching relates to system, method, medium for in-situ perception in an autonomous driving vehicle. A plurality of types of sensor data acquired continuously by a plurality of types of sensors deployed on the vehicle are first received, where the plurality of types of sensor data provide information about surrounding of the vehicle. Based on at least one model, one or more items are tracked from a first of the plurality of types of sensor data acquired by one or more of a first type of the plurality of types of sensors, wherein the one or more items appear in the surrounding of the vehicle. At least some of the one or more items are then automatically labeled on-the-fly via either cross modality validation or cross temporal validation of the one or more items and are used to locally adapt, on-the-fly, the at least one model in the vehicle.

An image classification method is provided. The method includes: inputting a to-be-classified image into a plurality of neural network models; obtaining data output by multiple non-input layers specified by each neural network model to generate a plurality of image features corresponding to the plurality of neural network models; respectively inputting the plurality of corresponding image features into linear classifiers, each of the linear classifiers being trained by one of the plurality of neural network models for determining whether an image belongs to a preset class; obtaining, using each neural network model, a corresponding probability that the to-be-classified image comprises an object image of the preset class; and determining, according to each obtained probability, whether the to-be-classified image includes the object image of the preset class.

A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as a negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for adjusting a target neural network using automatically generated test cases before deployment of the target neural network in a deployment environment. One of the methods may include generating a plurality of test inputs by using a test case generation neural network; processing the plurality of test inputs using a target neural network to generate one or more test outputs for each test input; and identifying, from the one or more test outputs generated by the target neural network for each test input, failing test inputs that result in generation of test outputs by the target neural network that fail one or more criteria.

A computer-implemented method is provided. The method includes: obtaining a sample text and a sample image corresponding to the sample text; labeling a true semantic tag for the sample text according to a first preset rule; obtaining a text feature representation of the sample text and a predicted semantic tag output by a text coding sub-model; obtaining an image feature representation of the sample image output by an image coding sub-model; calculating a first loss based on the true semantic tag and the predicted semantic tag; calculating a contrast loss based on the text feature representation of the sample text and the image feature representation of the sample image; adjusting parameters of the text coding sub-model based on the first loss and the contrast loss; and adjusting parameters of the image coding sub-model based on the contrast loss.

Training a machine learning neural network (MLNN) in radiowave based monitoring of fall characteristics in diagnosing injury. The method comprises receiving, in a first set of input layers of the MLNN, from a millimeter wave (mmWave) radar sensing device, a set of mmWave radar point cloud data representing fall attributes associated with a subject, each of the first set associated with a respective fall attribute; receiving, at a second set of input layers of the MLNN, a set of personal attributes of the subject, training a MLNN classifier based on supervised training that establishes a correlation between an injury condition of the subject as generated at the output layer, the mmWave point cloud data, and personal attributes; and adjusting an initial matrix of weights by backpropagation to increase correlation between the injury condition, the mmWave point cloud data, and the personal attributes.