-
公开(公告)号:US12118730B2
公开(公告)日:2024-10-15
申请号:US17456313
申请日:2021-11-23
Inventor: Younghyun Park , Jun Seo , Jaekyun Moon
CPC classification number: G06T7/13 , G06N3/04 , G06T3/40 , G06T7/11 , G06T7/194 , G06T2207/20081 , G06T2207/20084
Abstract: An edge detecting device includes a feature extracting circuit configured to extract first and second feature data from an input image; a prototype generating circuit configured to generate prototype data using the first feature data and an input label, the prototype data including foreground and background information of an object; a region detecting circuit configured to generate a segmentation mask by detecting a region of an object using the first feature data and the prototype data; and an edge extracting circuit configured to generate an edge map by combining the segmentation mask and the second feature data.
-
公开(公告)号:US12131528B2
公开(公告)日:2024-10-29
申请号:US17454029
申请日:2021-11-08
Inventor: Jun Seo , Younghyun Park , Jaekyun Moon
IPC: G06V20/00 , G06F18/214 , G06N3/045 , G06N3/048
CPC classification number: G06V20/00 , G06F18/214 , G06N3/045 , G06N3/048
Abstract: An object detecting device includes a feature extracting circuit configured to extract first feature data from an input image; a feature transforming circuit configured to transform the first feature data into transformed feature data according to a transformation function; and a decoder circuit configured to decode the transformed feature data into a region map indicating a detected object.
-
公开(公告)号:US11741356B2
公开(公告)日:2023-08-29
申请号:US16431319
申请日:2019-06-04
Inventor: Jaekyun Moon , Sung Whan Yoon , Jun Seo
IPC: G06N3/08 , G06N20/10 , G06T9/00 , G06T11/00 , G06F18/2451 , G06V10/764 , G06V10/77 , G06V10/82 , G06V20/00
CPC classification number: G06N3/08 , G06F18/2451 , G06N20/10 , G06T9/001 , G06T11/003 , G06V10/764 , G06V10/7715 , G06V10/82 , G06V20/35
Abstract: A data processing method by learning of a neural network may be provided. The data processing method by the learning of a neural network includes: obtaining a first set of output values by processing a first set of input values of a task by the neural network; forming a projection space on the basis of the first set of output values; obtaining a second set of output values by processing a second set of input values out of input values of the task by the neural network; projecting the second set of output values onto the projection space; and performing processing the second set of output values in the projection space.
-
-