-
公开(公告)号:US12039010B2
公开(公告)日:2024-07-16
申请号:US17563663
申请日:2021-12-28
Inventor: Won Jun Hwang , Jae Min Na
IPC: G06K9/62 , G06F18/214
CPC classification number: G06F18/2148
Abstract: The present invention relates to a method and apparatus for unsupervised domain adaptation, including the steps of generating a first augmented domain associated with a source domain, generating a second augmented domain associated with a target domain, and performing unsupervised domain adaptation by using the first augmented domain and the second augmented domain as a bridge for connecting the source domain and the target domain, and it is possible to apply to other exemplary embodiments.
-
2.
公开(公告)号:US11620774B2
公开(公告)日:2023-04-04
申请号:US16877869
申请日:2020-05-19
Inventor: Won Jun Hwang , Dong Yi Kim , Joon Pyo Hong , Hyung Ho Kim
Abstract: A generative adversarial network (GAN)-based system for generating a color image from an edge image includes: a first GAN training a model for converting the edge image into an intermediate image; and a second GAN training a model for converting the intermediate image into the color image, wherein an entropy of the intermediate image corresponds to a value between an entropy of the edge image and an entropy of the color image.
-
公开(公告)号:US12272172B2
公开(公告)日:2025-04-08
申请号:US17839443
申请日:2022-06-13
Inventor: Won Jun Hwang , Kun Liang Liu
Abstract: Provided are a device and method for human parsing. The method includes receiving at least one piece of image data and ground truth values for human parsing, generating a height distribution map and a width distribution map for the image data, acquiring attention maps and scaled feature maps for each of a height and a width of the image data using the distribution maps, calculating a distribution loss rate by concatenating the scaled feature maps, acquiring an improved feature map on the basis of the calculated distribution loss rate, and performing human parsing on an object included in the image data using the improved feature map.
-
公开(公告)号:US20240028954A1
公开(公告)日:2024-01-25
申请号:US18071058
申请日:2022-11-29
Inventor: Hyeon Cho , Won Jun Hwang , Geon Woo Baek
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: Provided is an electronic apparatus for lightweight of a three dimensional (3D) object detection model based on knowledge distillation, the electronic device including: a backbone network module configured to perform knowledge distillation such that a first feature map of a teacher network and a second feature map of a student network extracted through input point cloud data are made identical to as each other; and a self-attention module configured to acquire a plurality of pieces of detection information from a plurality of detection heads for 3D object detection, respectively, using the first feature map and the second feature map, and perform knowledge distillation using a relation-aware self-attention calculated based on the acquired plurality of pieces of detection information.
-
公开(公告)号:US11301717B2
公开(公告)日:2022-04-12
申请号:US16716881
申请日:2019-12-17
Applicant: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION , Dongguk University Industry-Academic Cooperation Foundation
Inventor: Won Jun Hwang , Ho Chul Sin , Dong Yi Kim , Soo Chul Lim , Dae Kwan Ko
Abstract: A method of measuring an interaction force includes: generating feature maps corresponding to a plurality of sequential images; generating pooling maps respectively corresponding to feature map groups including a predetermined number of feature maps among the feature maps; generating attention maps corresponding to the pooling maps; and sequentially receiving feature maps modified based on the attention maps and outputting interaction force information.
-
-
-
-