Samsung Electronics Co., Ltd.

Hyundai Motor Company

Samsung Sds Co., Ltd.

Lg Electronics Inc.

JoonHo Lee

Hyun Sun Cho

Hanshin Chung

Jongwoo Nam

Yekyung Yoo

Seunghwa Jeong

Dongmin Lee

Bobeen Kim

Yuna Park

Myunggyu Kim

Hyeok Jin Choi

Jieun Song

Nami Mo

SooAh Cho

JoonSeok Lee

Sujung Youn

Sanghum Yoon

Jungah Choi

Jinnam Kim

Haeyoon Park

Minyoung Lee

Jiyoon Yoon

Jung Kyung Kwack

Joon-Taek Lee

Jun-Ho Kang

Daekwan Kim

Taechan Kim

Hyun Ki Cho

Kyoung-ae Lim

Jong Woo Nam

Sang-Bum Cho

Kyu-Jung Kim

Minji Park

Hyeokjin Choi

Dong Guk Lee

HyoSeob Song

Jae-Young Yang

Chang-Hoon Kim

Mee-Kyoung Park

Chang-Hyun Baek

Dae-Yeol Shim

Dongguk Lee

A knowledge distillation method based on a regression task according to an embodiment of the present disclosure includes training a first deep neural network model that is a teacher model including a first encoder and a first decoder, constructing a second deep neural network model that is a student model including a second encoder and a second decoder according to a preset constraint of a target system and initializing parameters of the second deep neural network model, performing a first knowledge distillation operation on the second encoder of the second deep neural network model based on the trained first deep neural network model, and performing a second knowledge distillation operation on the second encoder and the second decoder of the second deep neural network model based on the trained first deep neural network model.

Knowledge distillation method based on regression task and computing device for executing the method

An apparatus is for unsupervised domain adaptation for allowing a deep learning model with supervised learning on a source domain completed to be subjected to unsupervised domain adaptation to a target domain. The apparatus includes a first learning unit to perform a forward pass by inputting a pair (x, y) of first data xof the source domain and a label yfor each of the first data and second data xbelonging to the target domain, and insert a dropout following a Bernoulli distribution into the deep learning model in performing the forward pass, and a second learning unit to perform a back propagation to minimize uncertainty about the learning parameter of the deep learning model by using a predicted value for each class output through the forward pass and the label y, and an uncertainty vector for the second data xoutput through the forward pass as inputs.

Apparatus and method for unsupervised domain adaptation

An image classification apparatus includes an image segmentation module configured to segment a learning image into a plurality of segment images, a primary classification module configured to perform machine learning on a primary classifier using the plurality of segment images, and a secondary classification module configured to calculate a weight value combination for creating a secondary classification estimation value for the learning image from a plurality of primary classification estimation values generated by passing the plurality of segment images to the trained primary classifier, or a machine learning-based learning parameter.

Apparatus and method for classifying image

A few-shot learning method according to an embodiment may be performed in a computing device including one or more processors and a memory storing one or more programs executed by the one or more processors. The method may include performing a first task for subjecting a first model to few-shot learning (FSL) based on one or more meta-training data and performing a second task for subjecting a second model to supervised learning based on one or more derived data modified from the one or more meta-training data.

Method for few-shot learning and apparatus for executing the method

Clothing care machine

Display screen or portion thereof with icon

Washing machine

Washing machine with graphical user interface

An air flow control system of a vehicle may include an engine mixing air and fuel and generating a rotation force by combusting the mixture of the air and the fuel in a combustion chamber, main ducts provided in a front side of the vehicle to transmit air to the combustion chamber of the engine, heat dissipation members provided adjacent to the main ducts to cool a fluid flowing inside thereof through heat exchange with external air, assistant ducts branched from the main ducts to transmit air flowing in the main ducts to the heat dissipation members, and control valves provided in the assistant ducts to control air supplied to the heat dissipation members.

Air flow control system of vehicle

A cooling and thermoelectric power generating system for a vehicle may include a low temperature radiator disposed at an ambient air intake which is configured to allow ambient air in front of the vehicle to be introduced to an engine room, a coolant line adapted that coolant passing through the low temperature radiator is circulated again through the low temperature radiator via a water-cooled condenser, a refrigerant line adapted that refrigerant is flowed through the condenser, and a thermoelectric generator adapted that coolant flowing through the coolant line and refrigerant flowing through the refrigerant line are passed therethrough, in which the thermoelectric generator performs thermoelectric generation by using temperature difference between coolant flowing through the coolant line and refrigerant flowing through the refrigerant line.

Cooling and thermoelectric power generating system for vehicle

A cooling system for a vehicle may include at least two air ducts formed at both side of an exterior air intake port; a low temperature radiator to release heat of coolant into the air; a high temperature radiator to release heat of coolant into the air; an ancillary low temperature radiator to release heat of coolant into the air; an ancillary high temperature radiator disposed inside of another one of the at least two air duct to release heat of coolant into the air; a turbocharger; an intercooler cooling compressed air generated from the turbocharger by using coolant flowed via the low temperature radiator and the high temperature radiator; a compressor; a condenser cooling the compressed refrigerant generated from the compressor by using coolant flowed via the low temperature radiator; a high temperature coolant passage; and a low temperature coolant passage.

Cooling system for vehicle

A method of generating an image using an image capturing device includes generating an imperfect image excluding data corresponding to one or more pixel sensors by capturing an object while the object is focused. A defocused image is generated to include the data corresponding to the one or more pixel sensors generated using neighboring pixel sensors around the one or more pixel sensors while the object is defocused. The data corresponding to the one or more pixel sensors is extracted based on data in the generated imperfect image and data in the generated defocused image. A final image is then generated by reflecting the extracted data to at least one of the generated imperfect image or the generated defocused image.

Method of generating image by compensating excluded pixel data and image generation device therewith

Growing community of inventors

Seoul, South Korea

JoonHo Lee