CN108604304A - 用于使来自源域的用于对象表示的深度模型适应于目标域的方法和系统 - Google Patents

用于使来自源域的用于对象表示的深度模型适应于目标域的方法和系统 Download PDF

Info

Publication number
CN108604304A
CN108604304A CN201680079452.0A CN201680079452A CN108604304A CN 108604304 A CN108604304 A CN 108604304A CN 201680079452 A CN201680079452 A CN 201680079452A CN 108604304 A CN108604304 A CN 108604304A
Authority
CN
China
Prior art keywords
criterion
aiming field
depth model
feature
input picture
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201680079452.0A
Other languages
English (en)
Chinese (zh)
Inventor
汤晓鸥
张展鹏
罗平
吕健勤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sensetime Group Ltd
Original Assignee
Sensetime Group Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sensetime Group Ltd filed Critical Sensetime Group Ltd
Publication of CN108604304A publication Critical patent/CN108604304A/zh
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
CN201680079452.0A 2016-01-20 2016-01-20 用于使来自源域的用于对象表示的深度模型适应于目标域的方法和系统 Pending CN108604304A (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/071501 WO2017124336A1 (fr) 2016-01-20 2016-01-20 Procédé et système d'adaptation d'un modèle profond permettant la représentation d'objet depuis un domaine source à un domaine cible

Publications (1)

Publication Number Publication Date
CN108604304A true CN108604304A (zh) 2018-09-28

Family

ID=59361172

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201680079452.0A Pending CN108604304A (zh) 2016-01-20 2016-01-20 用于使来自源域的用于对象表示的深度模型适应于目标域的方法和系统

Country Status (2)

Country Link
CN (1) CN108604304A (fr)
WO (1) WO2017124336A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113255823A (zh) * 2021-06-15 2021-08-13 中国人民解放军国防科技大学 无监督域适应的方法及装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11155809B2 (en) 2014-06-24 2021-10-26 Bio-Rad Laboratories, Inc. Digital PCR barcoding
CN113011568A (zh) * 2021-03-31 2021-06-22 华为技术有限公司 一种模型的训练方法、数据处理方法及设备
CN113159199B (zh) * 2021-04-27 2022-12-27 广东工业大学 一种基于结构特征增强和类中心匹配的跨域图像分类方法

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101582813A (zh) * 2009-06-26 2009-11-18 西安电子科技大学 基于分布式迁移网络学习的入侵检测系统及其方法
CN101840569A (zh) * 2010-03-19 2010-09-22 西安电子科技大学 基于迁移学习的投影寻踪高光谱图像分割方法
CN103354988A (zh) * 2011-01-31 2013-10-16 华为技术有限公司 用于计算穿过多个域的点对点标签交换路径的系统和方法
CN103793718A (zh) * 2013-12-11 2014-05-14 台州学院 一种基于深度学习的人脸表情识别方法
CN104199023A (zh) * 2014-09-15 2014-12-10 南京大学 一种基于深度感知的rfid室内定位系统及其工作方法
US20150055783A1 (en) * 2013-05-24 2015-02-26 University Of Maryland Statistical modelling, interpolation, measurement and anthropometry based prediction of head-related transfer functions
CN104616033A (zh) * 2015-02-13 2015-05-13 重庆大学 基于深度学习和支持向量机的滚动轴承故障诊断方法
CN105160866A (zh) * 2015-08-07 2015-12-16 浙江高速信息工程技术有限公司 一种基于深度学习神经网络结构的交通流预测方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102902966A (zh) * 2012-10-12 2013-01-30 大连理工大学 一种基于深度信赖网络的超分辨率人脸识别方法
CN104318215B (zh) * 2014-10-27 2017-09-19 中国科学院自动化研究所 一种基于域鲁棒卷积特征学习的交叉视角人脸识别方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101582813A (zh) * 2009-06-26 2009-11-18 西安电子科技大学 基于分布式迁移网络学习的入侵检测系统及其方法
CN101840569A (zh) * 2010-03-19 2010-09-22 西安电子科技大学 基于迁移学习的投影寻踪高光谱图像分割方法
CN103354988A (zh) * 2011-01-31 2013-10-16 华为技术有限公司 用于计算穿过多个域的点对点标签交换路径的系统和方法
US20150055783A1 (en) * 2013-05-24 2015-02-26 University Of Maryland Statistical modelling, interpolation, measurement and anthropometry based prediction of head-related transfer functions
CN103793718A (zh) * 2013-12-11 2014-05-14 台州学院 一种基于深度学习的人脸表情识别方法
CN104199023A (zh) * 2014-09-15 2014-12-10 南京大学 一种基于深度感知的rfid室内定位系统及其工作方法
CN104616033A (zh) * 2015-02-13 2015-05-13 重庆大学 基于深度学习和支持向量机的滚动轴承故障诊断方法
CN105160866A (zh) * 2015-08-07 2015-12-16 浙江高速信息工程技术有限公司 一种基于深度学习神经网络结构的交通流预测方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113255823A (zh) * 2021-06-15 2021-08-13 中国人民解放军国防科技大学 无监督域适应的方法及装置
CN113255823B (zh) * 2021-06-15 2021-11-05 中国人民解放军国防科技大学 无监督域适应的方法及装置

Also Published As

Publication number Publication date
WO2017124336A1 (fr) 2017-07-27

Similar Documents

Publication Publication Date Title
Xian et al. Latent embeddings for zero-shot classification
Neumann et al. Efficient scene text localization and recognition with local character refinement
Lun et al. Elements of style: learning perceptual shape style similarity
US9940577B2 (en) Finding semantic parts in images
Goel et al. Whole is greater than sum of parts: Recognizing scene text words
Liu et al. Person re-identification: What features are important?
CN108647583B (zh) 一种基于多目标学习的人脸识别算法训练方法
US9025864B2 (en) Image clustering using a personal clothing model
CN108604304A (zh) 用于使来自源域的用于对象表示的深度模型适应于目标域的方法和系统
CN103824051B (zh) 一种基于局部区域匹配的人脸搜索方法
US8325998B2 (en) Multidirectional face detection method
US20110085710A1 (en) Using relevance feedback in face recognition
CN105426890B (zh) 一种字符扭曲粘连的图形验证码识别方法
CN104881639B (zh) 一种基于层次tdp模型的人脸检测、分割和表情识别方法
Lettry et al. Repeated pattern detection using CNN activations
CN110458158A (zh) 一种针对盲人辅助阅读的文本检测与识别方法
Krishnan et al. Conditional distance based matching for one-shot gesture recognition
CN112000796A (zh) 答案生成方法、电子设备和计算机可读存储介质
CN107066955A (zh) 一种从局部人脸区域还原整张人脸的方法
Shimoda et al. Learning food image similarity for food image retrieval
Karaoglu et al. Con-text: text detection using background connectivity for fine-grained object classification
CN109146913B (zh) 一种人脸跟踪方法及装置
CN112926557B (zh) 一种训练多模态人脸识别模型的方法以及多模态人脸识别方法
CN113468925B (zh) 一种遮挡人脸识别方法、智能终端及存储介质
CN109427068A (zh) 基于超像素自动标注的深度学习共分割方法

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180928