Stradvision, Inc.

Superb Ai Co., Ltd.

Superb Al Co., Ltd.

Stadvision, Inc.

Stradivision, Inc.

Kye-Hyeon Kim

Hongmo Je

Wooju Ryu

Yongjoong Kim

Hojin Cho

SukHoon Boo

Taewoong Jang

Kyungjoong Jeong

Myungchul Sung

Donghun Yeo

Hak-Kyoung Kim

Woonhyun Nam

Insu Kim

Hyungsoo Lee

Myeong-Chun Lee

DongSoo Shin

Dongsoo Shin

Bongnam Kang

Jung Kwon Lee

Sung An Gweon

Woonhyu Nam

A method for learning parameters of a CNN using a 1&#xd7;K convolution operation or a K&#xd7;1 convolution operation is provided to be used for hardware optimization which satisfies KPI. The method includes steps of: a learning device (a) instructing a reshaping layer to two-dimensionally concatenate features in each group comprised of corresponding K channels of a training image or its processed feature map, to thereby generate a reshaped feature map, and instructing a subsequent convolutional layer to apply the 1&#xd7;K or the K&#xd7;1 convolution operation to the reshaped feature map, to thereby generate an adjusted feature map; and (b) instructing an output layer to refer to features on the adjusted feature map or its processed feature map, and instructing a loss layer to calculate losses by referring to an output from the output layer and its corresponding GT.

Learning method and learning device for CNN using 1xK or Kx1 convolution to be used for hardware optimization, and testing method and testing device using the same

A method for on-device continual learning of a neural network which analyzes input data is provided to be used for smartphones, drones, vessels, or a military purpose. The method includes steps of: a learning device, (a) sampling new data to have a preset first volume, instructing an original data generator network, which has been learned, to repeat outputting synthetic previous data corresponding to a k-dimension random vector and previous data having been used for learning the original data generator network, such that the synthetic previous data has a second volume, and generating a batch for a current-learning; and (b) instructing the neural network to generate output information corresponding to the batch. The method can be performed by generative adversarial networks (GANs), online learning, and the like. Also, the present disclosure has effects of saving resources such as storage, preventing catastrophic forgetting, and securing privacy.

Method and device for on-device continual learning of a neural network which analyzes input data, and method and device for testing the neural network to be used for smartphones, drones, vessels, or military purpose

A method for explainable active learning, to be used for an object detector, by using a deep autoencoder is provided. The method includes steps of an active learning device (a) (i) inputting acquired test images into the object detector to detect objects and output bounding boxes, (ii) cropping regions, corresponding to the bounding boxes, in the test images, (iii) resizing the test images and the cropped images into a same size, and (iv) inputting the resized images into a data encoder of the deep autoencoder to output data codes, and (b) (i) confirming reference data codes corresponding to the number of the resized images less than a counter threshold by referring to a data codebook, (ii) extracting specific data codes from the data codes, (iii) selecting specific test images as rare samples, and (iv) updating the data codebook by referring to the specific data codes.

Method for explainable active learning, to be used for object detector, by using deep encoder and active learning device using the same

A method of generating training data for a deep learning network is provided. The method includes steps of: an auto labeling device (a) (i) allowing a labeling network to label test images and generate labeled test images including primary labeling information and primary confidence scores on primary objects, (ii) allowing a labeler to verify the primary labeling information to generate correction-related class information, (iii) setting a first and a second threshold confidence scores; (b) (i) allowing the labeling network to label unlabeled images and generate labeled images including secondary labeling information and secondary confidence scores on secondary objects, (ii) allowing an object difficulty estimation module to generate object difficulty scores and object difficulty classes, (iii) allowing an image difficulty estimation module to generate image difficulty scores and image difficulty classes; and (c) transmitting the first labeled images to the labeler to generate verified labeled images, and generating the training data.

Method for generating training data to be used for training deep learning network capable of analyzing images and auto labeling device using the same

A method for learning a recurrent neural network to check an autonomous driving safety to be used for switching a driving mode of an autonomous vehicle is provided. The method includes steps of: a learning device (a) if training images corresponding to a front and a rear cameras of the autonomous vehicle are acquired, inputting each pair of the training images into corresponding CNNs, to concatenate the training images and generate feature maps for training, (b) inputting the feature maps for training into long short-term memory models corresponding to sequences of a forward RNN, and into those corresponding to the sequences of a backward RNN, to generate updated feature maps for training and inputting feature vectors for training into an attention layer, to generate an autonomous-driving mode value for training, and (c) allowing a loss layer to calculate losses and to learn the long short-term memory models.

Learning method and learning device of recurrent neural network for autonomous driving safety check for changing driving mode between autonomous driving mode and manual driving mode, and testing method and testing device using them

A learning method for acquiring at least one personalized reward function, used for performing a Reinforcement Learning (RL) algorithm, corresponding to a personalized optimal policy for a subject driver is provided. And the method includes steps of: (a) a learning device performing a process of instructing an adjustment reward network to generate first adjustment rewards, by referring to the information on actual actions and actual circumstance vectors in driving trajectories, a process of instructing a common reward module to generate first common rewards by referring to the actual actions and the actual circumstance vectors, and a process of instructing an estimation network to generate actual prospective values by referring to the actual circumstance vectors; and (b) the learning device instructing a first loss layer to generate an adjustment reward and to perform backpropagation to learn parameters of the adjustment reward network.

Learning method and learning device for supporting reinforcement learning by using human driving data as training data to thereby perform personalized path planning

A method for auto-labeling images by using a class-agnostic refinement module is provided. The method includes steps of: (a) an auto-labeling device inputting the images into a coverage controlling module, to thereby allow the coverage controlling module to label objects on the images and thus to output first labeling data including first object region data and first class data; (b) the auto-labeling device inputting the images and the first object region data into the class-agnostic refinement module, to thereby allow the class-agnostic refinement module to label the objects on the images and thus to generate second object region data, and allowing the class-agnostic refinement module to align the first object region data and the second object region data to thereby output refined object region data; and (c) the auto-labeling device generating second labeling data including the first class data and the refined object region data.

Method for auto-labeling test image by using class-agnostic refinement module, and auto labeling device using the same

A method for training an auto labeling device capable of performing automatic verification by using uncertainty scores of labels is provided. The method includes steps of: a learning device (a) inputting unlabeled training images into a trained object detection network and a trained convolution network to generate bounding boxes for training and feature maps for training; and (b) (i) instructing an ROI pooling layer to generate pooled feature maps for training, (ii) at least one of (ii-1) inputting the pooled feature maps for training into a first classifier to generate first class scores for training and first box uncertainty scores for training, and (ii-2) inputting the pooled feature maps for training into a second classifier to generate second class scores for training and second box uncertainty scores for training, and (iii) training one of the first classifier using first class losses and the second classifier using second class losses.

Methods for training auto labeling device and performing auto labeling related to object detection while performing automatic verification by using uncertainty scores and devices using the same

A method for training an auto labeling device performing automatic verification using uncertainty of labels is provided. The method includes steps of: a learning device (a) (i) inputting unlabeled training images into (i-1) an object detection network to generate bounding boxes for training and (i-2) a convolution network to generate feature maps for training, and (ii) allowing an ROI pooling layer to generate pooled feature maps for training and inputting the pooled feature maps for training into a deconvolution network to generate segmentation masks for training; and (b) (i) inputting the pooled feature maps for training into at least one of (i-1) a first classifier to generate first per-pixel class scores for training and first mask uncertainty scores for training and (i-2) a second classifier to generate second per-pixel class scores for training and second mask uncertainty scores for training and (ii) training the first classifier or the second classifier.

Methods for training auto labeling device and performing auto labeling related to segmentation while performing automatic verification by using uncertainty scores and devices using the same

A method for training an auto-labeling device is provided. The method includes: (a) inputting a training image to a pre-trained feature extraction module to generate a feature, (b) inputting the feature to a pre-trained first classification module to output a first class score and a first uncertainty score, inputting the feature to a pre-trained second classification module, to output a second class score and a second uncertainty score, generating a scaled second uncertainty score by applying a scale parameter to the second uncertainty score, and then inputting the feature to a fitness estimation module to output a fitness value; and (c) (i) updating the scale parameter by using an uncertainty loss generated based on the first uncertainty score and the scaled second uncertainty score, and (ii) training the fitness estimation module by using a cross-entropy loss generated based on the uncertainty loss and the fitness value.

Methods for training auto-labeling device and performing auto-labeling by using hybrid classification and devices using the same

A method for generating a lane departure warning (LDW) alarm by referring to information on a driving situation is provided to be used for ADAS, V2X or driver safety which are required to satisfy level 4 and level 5 of autonomous vehicles. The method includes steps of: a computing device instructing a LDW system (i) to collect information on the driving situation including information on whether a specific spot corresponding to a side mirror on a side of a lane, into which the driver desires to change, belongs to a virtual viewing frustum of the driver and (ii) to generate risk information on lane change by referring to the information on the driving situation; and instructing the LDW system to generate the LDW alarm by referring to the risk information. Thus, the LDW alarm can be provided to neighboring autonomous vehicles of level 4 and level 5.

Method and device for learning generating lane departure warning (LDW) alarm by referring to information on driving situation to be used for ADAS, V2X or driver safety required to satisfy level 4 and level 5 of autonomous vehicles

A method for achieving better performance in autonomous driving while saving computing power, by using confidence scores representing a credibility of an object detection which is generated in parallel with an object detection process is provided. And the method includes steps of: (a) a computing device acquiring at least one circumstance image on surroundings of a subject vehicle, through at least one image sensor installed on the subject vehicle; (b) the computing device instructing a convolutional neural network (CNN) to apply at least one CNN operation to the circumstance image, thereby to generate initial object information and initial confidence information on the circumstance image; and (c) the computing device generating final object information on the circumstance image by referring to the initial object information and the initial confidence information with a support of a Reinforcement learning (RL) reinforcement learning (RL) agent, and through V2X communications with at least part of surrounding objects.

Method and device for attention-driven resource allocation by using reinforcement learning and V2X communication to thereby achieve safety of autonomous driving

A learning method of a CNN (Convolutional Neural Network) for monitoring one or more blind spots of a monitoring vehicle is provided. The learning method includes steps of: a learning device, if training data corresponding to output from a detector on the monitoring vehicle is inputted, instructing a cue information extracting layer to uses class information and location information on a monitored vehicle included in the training data, thereby outputting cue information on the monitored vehicle; instructing an FC layer for monitoring the blind spots to perform neural network operations by using the cue information, thereby outputting a result of determining whether the monitored vehicle is located on one of the blind spots; and instructing a loss layer to generate loss values by referring to the result and its corresponding GT, thereby learning parameters of the FC layer for monitoring the blind spots by backpropagating the loss values.

Learning method and testing method for monitoring blind spot of vehicle, and learning device and testing device using the same

Processes of explainable active learning, for an object detector, by using a Bayesian dual encoder is provided. The processes include: (a) inputting test images into the object detector to generate cropped images, resizing the test images and the cropped images, and inputting the resized images into a data encoder to output data codes; (b) (b1) one of (i) inputting the test images into the object detector, applying Bayesian output embedding and resizing the activation entropy maps and the cropped activation entropy maps, and (ii) inputting resized object images and applying the Bayesian output embedding and (b2) inputting the resized activation entropy maps into a model encoder to output model codes; and (c) (i) confirming reference data codes, selecting specific test images as rare samples, and updating the data codebook, and (ii) confirming reference model codes and selecting specific test images as hard samples.

Method for explainable active learning, to be used for object detector, by using Bayesian dual autoencoder and active learning device using the same

A method for training a deep learning network based on artificial intelligence is provided. The method includes steps of: a learning device (a) inputting unlabeled data into an active learning network to acquire sub unlabeled data and inputting the sub unlabeled data into an auto labeling network to generate new labeled data; (b) allowing a continual learning network to sample the new labeled data and existing labeled data to generate a mini-batch, and train the existing learning network using the mini-batch to acquire a trained learning network, wherein part of the mini-batch are selected by referring to specific existing losses; and (c) (i) allowing an explainable analysis network to generate insightful results on validation data and transmit the insightful results to a human engineer to transmit an analysis of the trained learning network and (ii) modifying at least one of the active learning network and the continual learning network.

Growing community of inventors

Seoul, South Korea

Kye-Hyeon Kim