Stradvision, Inc.

Sung An Gweon

Yongjoong Kim

Bongnam Kang

Hongmo Je

Wooju Ryu

SukHoon Boo

Kye-Hyeon Kim

Dongkyu Yu

A method for performing on-device learning of embedded machine learning network of autonomous vehicle by using multi-stage learning with adaptive hyper-parameter sets is provided. The processes include: (a) dividing the current learning into a 1-st stage learning to an n-th stage learning, assigning 1-st stage training data to n-th stage training data, generating a 1_1-st hyper-parameter set candidate to a 1_h-th hyper-parameter set candidate, training the embedded machine learning network in the 1-st stage learning, and determining a 1-st adaptive hyper-parameter set; (b) generating a k_1-st hyper-parameter set candidate to a k_h-th hyper-parameter set candidate, training the (k&#x2212;1)-th stage-completed machine learning network in the k-th stage learning, and determining a k-th adaptive hyper-parameter set; and (c) generating an n-th adaptive hyper-parameter set, and executing the n-th stage learning, to thereby complete the current learning.

Method for performing on-device learning of machine learning network on autonomous vehicle by using multi-stage learning with adaptive hyper-parameter sets and device using the same

A method of on-vehicle active learning for training a perception network of an autonomous vehicle is provided. The method includes steps of: an on-vehicle active learning device, (a) if a driving video and sensing information are acquired from a camera and sensors on an autonomous vehicle, inputting frames of the driving video and the sensing information into a scene code assigning module to generate scene codes including information on scenes in the frames and on driving events; and (b) at least one of selecting a part of the frames, whose object detection information satisfies a condition, as specific frames by using the scene codes and the object detection information and selecting a part of the frames, matching a training policy, as the specific frames by using the scene codes and the object detection information, and storing the specific frames and specific scene codes in a frame storing part.

Method and device for on-vehicle active learning to be used for training perception network of autonomous vehicle

A method for calibrating a pitch of a camera on a vehicle is provided. The method includes steps of: a calibration device (a) inputting driving images from the camera into an object detection network to detect objects and generate object detection information and into a lane detection network to detect lanes and generate lane detection information; (b) profiling the object and the lane detection information to generate object profiling information and lane profiling information, inputting the object profiling information into an object-based pitch estimation module to select a first target object and a second target object to generate a first pitch and a second pitch, and (iii) inputting vanishing point detection information and the lane profiling information into a lane-based pitch estimation module to generate a third pitch and a fourth pitch; and (c) inputting the first to the fourth pitches into a pitch-deciding module to generate a decided pitch.

Method and device for calibrating pitch of camera on vehicle and method and device for continual learning of vanishing point estimation model to be used for calibrating the pitch

A method of adjustable continual learning of a deep neural network model by using a selective deep generative replay module is provided. The method includes steps of: a learning device (a) (i) inputting training data from a total database and a sub-database into the selective deep generative replay module to generate first and second low-dimensional distribution features, (ii) inputting binary values, random parameters, and the second low-dimensional distribution features into a data generator to generate a third training data, and (iii) inputting a first training data into a solver to generate labeled training data; (b) inputting the training data, the low-dimensional distribution features, and the binary values into a discriminator to generate a first and a second training data scores, a first and a second feature distribution scores, and a third training data score; and (c) training the discriminator, the data generator, the distribution analyzer and the solver.

Method for performing adjustable continual learning on deep neural network model by using selective deep generative replay module and 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 optimizing an on-device neural network model by using a Sub-kernel Searching Module is provided. The method includes steps of a learning device (a) if a Big Neural Network Model having a capacity capable of performing a targeted task by using a maximal computing power of an edge device has been trained to generate a first inference result on an input data, allowing the Sub-kernel Searching Module to identify constraint and a state vector corresponding to the training data, to generate architecture information on a specific sub-kernel suitable for performing the targeted task on the training data, (b) optimizing the Big Neural Network Model according to the architecture information to generate a specific Small Neural Network Model for generating a second inference result on the training data, and (c) training the Sub-kernel Searching Module by using the first and the second inference result.

Growing community of inventors

Seoul, South Korea

Sung An Gweon