-
公开(公告)号：US20230334321A1
公开(公告)日：2023-10-19
申请号：US17976655
申请日：2022-10-28
Inventor： Su Woong LEE , Jong-Gook KO , Wonyoung YOO , Seungjae LEE , Yongsik LEE , Juwon LEE , Da-Un JUNG
IPC: G06N3/08
Abstract: Disclosed are a deep neural network lightweight device based on batch normalization, and a method thereof. The deep neural network lightweight device based on batch normalization includes a memory that stores at least one data and at least one processor that executes a network lightweight module. When executing the network lightweight module, the processor performs learning on an input neural network based on sparsity regularization to adaptively determine at least one parameter of the sparsity regularization, performs pruning on the learning result, and performs fine tuning on the pruning result.
-
2.发明申请METHOD OF EXTRACTING VISUAL DESCRIPTOR USING FEATURE SELECTION AND SYSTEM FOR THE SAME 有权使用特征选择和系统提取视觉描述符的方法公开(公告)号：US20150117785A1
公开(公告)日：2015-04-30
申请号：US14223836
申请日：2014-03-24
Inventor： Keun-Dong LEE , Seung-Jae LEE , Sang-Il NA , Sung-Kwan JE , Da-Un JUNG , Weon-Geun OH , Young-Ho SUH , Wook-Ho SON
IPC: G06K9/46
CPC classification number: G06K9/4671 , G06K9/228
Abstract: A method and system for extracting a visual descriptor using a feature selection are provided. The system includes an image input unit configured to receive an image, a candidate feature point group detecting unit configured to detect a point having a local maximum or minimum of local region filtering in scale-space images as being included in a candidate feature point group, a feature point selecting unit configured to calculate an importance for each candidate feature point, depending on its characteristics, select the candidate feature point as a feature point when its importance is greater than the predetermined threshold value, a dominant orientation calculating unit configured to calculate a dominant orientation of the selected feature point and a visual descriptor extracting unit configured to extract a patch for each feature point, according to its scale, location and dominant orientation, and extract a visual descriptor from the patch.
Abstract translation: 提供了一种使用特征选择来提取视觉描述符的方法和系统。 该系统包括被配置为接收图像的图像输入单元，候选特征点组检测单元，被配置为检测在尺度空间图像中包括在候选特征点组中的局部区域过滤的局部最大值或最小值的点， 特征点选择单元，其被配置为根据其特征来计算每个候选特征点的重要性;当所述候选特征点的重要性大于所述预定阈值时，选择所述候选特征点作为特征点;主导方位计算单元， 所选择的特征点的主导取向和视觉描述符提取单元，被配置为根据其尺度，位置和主导取向提取每个特征点的补丁，并从补丁提取可视描述符。
-
公开(公告)号：US20220222525A1
公开(公告)日：2022-07-14
申请号：US17554870
申请日：2021-12-17
Inventor： Su Woong LEE , Seungjae LEE , Jong-Gook KO , Wonyoung YOO , Jung Jae YU , Keun Dong LEE , Yongsik LEE , Da-Un JUNG
Abstract: Provided are a method and system for training a dynamic deep neural network. The method for training a dynamic deep neural network includes receiving an output of a last layer of the deep neural network and outputting a first loss, receiving an output of a routing module according to an input class of the deep neural network and outputting a second loss, calculating a third loss based on the first loss and the second loss, and updating a weight of the deep neural network by using the third loss.
-
公开(公告)号：US20210350241A1
公开(公告)日：2021-11-11
申请号：US17242604
申请日：2021-04-28
Inventor： Seungjae LEE , Jong-Gook KO , Keun Dong LEE , Su Woong LEE , Yongsik LEE , Da-Un JUNG , Wonyoung YOO
Abstract: An apparatus and method for searching a neural network architecture may be disclosed. The apparatus may include an architecture searcher and an architecture evaluator. The architecture searcher may search for a topology between nodes included in a basic cell of a network, search for an operation to be applied between the nodes after searching for the topology, and determine the basic cell. The architecture evaluator may evaluate performance of the determined basic cell.
-
-
-
Search Results
4
records
(took 0.04 seconds)
