WO2021052159A1 - Procédé et dispositif de prédiction de beauté faciale basée sur un apprentissage par transfert antagoniste - Google Patents

Procédé et dispositif de prédiction de beauté faciale basée sur un apprentissage par transfert antagoniste Download PDF

Info

Publication number
WO2021052159A1
WO2021052159A1 PCT/CN2020/112528 CN2020112528W WO2021052159A1 WO 2021052159 A1 WO2021052159 A1 WO 2021052159A1 CN 2020112528 W CN2020112528 W CN 2020112528W WO 2021052159 A1 WO2021052159 A1 WO 2021052159A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature
face
beauty prediction
prediction model
face beauty
Prior art date
Application number
PCT/CN2020/112528
Other languages
English (en)
Chinese (zh)
Inventor
翟懿奎
项俐
甘俊英
麦超云
曾军英
应自炉
Original Assignee
五邑大学
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 五邑大学 filed Critical 五邑大学
Publication of WO2021052159A1 publication Critical patent/WO2021052159A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification

Definitions

  • the invention relates to the field of image processing, in particular to a method and device for predicting the beauty of a face based on anti-migration learning.
  • Face beauty prediction technology is widely used in the field of photography.
  • deep learning technology the application of deep learning technology to facial beauty prediction technology makes facial beauty prediction results more accurate and more in line with people's cognition.
  • single-task learning ignores the association between tasks, and multi-task learning adds unnecessary combinations to the deep learning network, which increases the redundancy of deep learning tasks, and also increases the burden of network training, which seriously affects The efficiency of classification and recognition.
  • the purpose of the present invention is to solve at least one of the technical problems existing in the prior art, to provide a method and device for predicting the beauty of a face based on multi-task migration, and to reduce the amount of calculation through the similarity measurement.
  • the method for predicting the beauty of a face based on anti-migration learning includes the following steps:
  • the main task is the task of predicting the beauty of the face
  • the auxiliary task is the task of identifying the beauty factors of the face, N>A;
  • measuring the similarity between the N auxiliary tasks and the main task, and obtaining A auxiliary tasks with the highest similarity includes the following steps:
  • the first face beauty prediction model includes a first preprocessing layer for preprocessing face images connected in sequence, a first feature sharing layer for extracting shared image features, and A first independent feature extraction layer that extracts independent features from shared image features, and a first classification layer;
  • the second face beauty prediction model includes a second pre-processing layer connected in sequence, a second feature sharing layer, and a second independent The feature extraction layer is used to fuse independent features and the geometric features and texture features of the corresponding facial beauty prediction task, and the second classification layer.
  • the A first face beauty prediction model is used as the source domain and the second face beauty prediction model is used as the target domain, and the counter network is pre-trained to find the source domain relative to the target domain Migrating the universal feature parameters to the second face beauty prediction model specifically includes the following steps:
  • Mapping step map the source feature to the target feature space to obtain the pseudo target feature T(G(x s ));
  • Distinguish step distinguish the source of the target feature and the pseudo-target feature and calculate the error through the loss function
  • Optimization step use the regularization term r(G(x s ), T(G(x s ))) to measure the distance between the source feature and the pseudo-target feature, and then combine the error to optimize the mapping of the source feature to the target feature space;
  • mapping step Repeat the mapping step, the distinguishing step and the optimization step until the source domain and the target domain are adapted to obtain the common feature parameters
  • Migration step Migrate the general feature parameters to the second face beauty prediction model.
  • the above-mentioned face beauty prediction method based on anti-migration learning has at least the following beneficial effects: find the highest correlation among the auxiliary tasks of identifying face factors through the similarity measure, and construct the first face beauty prediction based on this.
  • the model is pre-trained; the training cost of pre-training is reduced, the deviation caused by the auxiliary tasks with unrelated factors to the first face beauty prediction model is reduced, and the negative migration is avoided.
  • the general feature parameters formed after the pre-training of the confrontation network are migrated to the second face beauty prediction model to achieve the final face beauty prediction. Through the confrontation migration learning, the calculation amount of the second face beauty prediction model training is reduced, and the training time is compressed. Use fewer training images to obtain a more accurate model effect.
  • a face beauty prediction device based on anti-transfer learning includes:
  • the similarity measurement module is used to measure the similarity between N auxiliary tasks and the main task to obtain A auxiliary tasks with the highest similarity.
  • the main task is the task of predicting the beauty of the face
  • the auxiliary task is the task of identifying the beauty factors of the face. N>A;
  • the first model establishment module is used to establish A first face beauty prediction model corresponding to A auxiliary tasks with the highest similarity
  • the second model building module is used to build a second face beauty prediction model for face beauty prediction
  • the parameter migration module is configured to use A of the first face beauty prediction model as the source domain and the second face beauty prediction model as the target domain to find the common feature parameters of the source domain relative to the target domain through pre-training of the confrontation network , Migrating the general feature parameters to the second face beauty prediction model;
  • the calculation module is used to input the face image to be tested to the second face beauty prediction model that is retrained to output the face beauty prediction result.
  • the similarity measurement module includes:
  • the feature expression acquisition module is used to construct a fully-supervised specific network for the N auxiliary tasks and the main task respectively and perform training to obtain the feature expression E s (I) of each task;
  • the tightness measurement module is used to construct a migration network between N auxiliary tasks and the main task, and measure the task tightness between the N auxiliary tasks and the main task, and the task tightness is calculated as follows: Where I is the input, D is the data set, f t (I) is the true value of the t-th input I, L t is the loss between the true value and the predicted value, and E I ⁇ D represents the expected value;
  • the normalization processing module is used to normalize the loss of the migration network through the analytic hierarchy process to obtain the correlation matrix
  • the optimization processing module is used to optimize the incidence matrix to obtain A auxiliary tasks with the highest similarity.
  • the first face beauty prediction model includes a first preprocessing layer for preprocessing face images that are sequentially connected, a first feature sharing layer for extracting shared image features, and A first independent feature extraction layer that extracts independent features from shared image features, and a first classification layer;
  • the second face beauty prediction model includes a second pre-processing layer connected in sequence, a second feature sharing layer, and a second independent The feature extraction layer is used to fuse independent features and the geometric features and texture features of the corresponding facial beauty prediction task, and the second classification layer.
  • the parameter migration module includes:
  • the mapping module is used to map the source feature to the target feature space to obtain the pseudo target feature T(G(x s ));
  • the distinguishing module is used to distinguish the source of the target feature and the pseudo-target feature and calculate the error through the loss function
  • the optimization module is used to use the regularization term r(G(x s ), T(G(x s ))) to measure the distance between the source feature and the pseudo-target feature, and then combine the error to optimize the source feature to the target feature space Mapping
  • the parameter acquisition module is used to acquire general characteristic parameters when both the source domain and the target domain are adapted;
  • the migration sub-module is used to migrate the general feature parameters to the second face beauty prediction model.
  • the above-mentioned facial beauty prediction device based on anti-migration learning has at least the following beneficial effects: the similarity measurement module finds the highest correlation among the auxiliary tasks of identifying facial factors, and the pre-training module builds the first
  • the face beauty prediction model is pre-trained; the training cost of pre-training is reduced, and the deviation caused by the auxiliary tasks with irrelevant factors to the first face beauty prediction model is avoided, and negative migration is avoided.
  • the parameter migration module migrates the general migration parameters formed after the pre-training of the confrontation network to the second face beauty prediction model, and realizes the final face beauty prediction. Through the confrontation migration learning, the calculation amount is reduced, the training time is compressed, and the calculation module is used more. Fewer training images can get a more accurate model effect.
  • FIG. 1 is a step diagram of a face beauty prediction method based on anti-migration learning according to an embodiment of the present invention
  • FIG. 2 is a specific step diagram of step S10
  • FIG. 3 is a schematic diagram of a face beauty prediction method based on anti-migration learning according to an embodiment of the present invention
  • FIG. 4 is another schematic diagram of a face beauty prediction method based on anti-migration learning according to an embodiment of the present invention.
  • FIG. 5 is a specific step diagram of step S30;
  • FIG. 6 is a structural diagram of an apparatus for predicting face beauty based on anti-migration learning according to an embodiment of the present invention.
  • Figure 7 is a structural diagram of the parameter migration module.
  • an embodiment of the present invention provides a face beauty prediction method based on anti-migration learning, which includes the following steps:
  • Step S10 measure the similarity between the N auxiliary tasks and the main task, and obtain A auxiliary tasks with the highest similarity, where the main task is the task of predicting the beauty of the face, and the auxiliary task is the task of identifying the beauty factors of the face, N>A;
  • Step S20 Establish A first face beauty prediction model corresponding to A secondary tasks with the highest similarity, and establish a second face beauty prediction model for face beauty prediction;
  • Step S30 Use A of the first face beauty prediction model as the source domain and the second face beauty prediction model as the target domain. Through pre-training of the confrontation network to find the common feature parameters of the source domain relative to the target domain, Transferring the general feature parameters to the second face beauty prediction model;
  • Step S40 Input the face image to be tested to the second trained face beauty prediction model to output the face beauty prediction result.
  • the similarity measure is used to find the most relevant among the auxiliary tasks of recognizing face factors, and based on this, the first face beauty prediction model is constructed for pre-training; the training cost of pre-training is reduced, Reduce the bias caused by the auxiliary tasks with irrelevant factors to the first face beauty prediction model, and avoid negative transfer.
  • the auxiliary tasks of multiple recognition of facial factors mainly include recognition of facial expression, age, gender, skin color, eye size, eye distance, ear shape, nose size, nose bridge height, lip shape, etc.
  • Transfer learning is to improve the learning of new tasks by transferring knowledge from related tasks that have been learned.
  • Migrating the general feature parameters formed after the adversarial network pre-training to the second face beauty prediction model can effectively reduce the calculation amount of the second face beauty prediction model training, compress the training time, and achieve more accurate results with fewer training images The effect of the model.
  • step S10 specifically includes the following steps:
  • Step S11 Construct a fully-supervised specific network for each of the N auxiliary tasks and the main task and perform training to obtain the feature expression E s (I) of each task.
  • Each specific network has an encoder and a decoder, and all codes are The decoders all have the same ResNet50 structure, and the decoders correspond to different tasks;
  • Step S12. Construct a migration network between N auxiliary tasks and the main task, and measure the task tightness between the N auxiliary tasks and the main task.
  • the task tightness calculation method is: Where I is the input, D is the data set, f t (I) is the true value of the t-th input I, L t is the loss between the true value and the predicted value, and E I ⁇ D represents the expected value;
  • Step S13 Normalize the loss of the migration network through the analytic hierarchy process to obtain the correlation matrix; specifically, for each task pair (i, j) of the source task pointing to the target task, the test set is taken out by the leave-out method after the migration ; For each task, construct a matrix W t , and then use the Laplace smoothing method to control the output result of the matrix W t within the range [0.001, 0.999], and then transform to obtain an incidence matrix, which reflects the similarity between tasks Probability.
  • the calculation method of each element w′ i, j in W′ t is:
  • Step S14 Perform optimization processing on the incidence matrix to obtain A auxiliary tasks with the highest similarity, that is, obtain a subgraph selection problem based on the incidence matrix.
  • the first face beauty prediction model corresponding to each auxiliary task includes a first preprocessing layer 11 for preprocessing face images connected in sequence, and a first feature sharing layer for extracting shared image features. 12.
  • the first face beauty prediction model of all auxiliary tasks can be combined into one, multiple first preprocessing layers 11 are combined into one, and multiple first feature sharing layers 12 are combined into one.
  • the shared image features of all tasks are placed in the first feature sharing layer 12; after the first feature sharing layer 12, multiple first independent feature extraction layers 13 and multiple first classification layers 14 are connected corresponding to different tasks.
  • the second face beauty prediction model includes a second preprocessing layer 21, a second feature sharing layer 22, and a second independent feature extraction layer 23, which are connected in sequence, and are used to fuse independent features with geometric features and textures corresponding to face beauty prediction tasks.
  • the first independent feature extraction layer 13 and the second independent feature extraction layer 23 both include 1 convolutional layer, 1 BN layer, 1 activation function layer, and 1 pooling layer that are connected in sequence, and the first classification layer 14
  • Both the second classification layer 25 and the second classification layer 25 include two fully connected layers.
  • step S30 specifically includes the following steps:
  • Step S32 Mapping step: map the source feature to the target feature space to obtain the pseudo target feature T(G(x s ));
  • Step S33 distinguishing step: the discriminator distinguishes the source of the target feature and the pseudo-target feature and calculates the error through the loss function; wherein the loss function can be a commonly used loss function, such as a cross entropy loss function or a mean square error loss function;
  • Step S34 optimization step: use the regularization term r(G(x s ), T(G(x s ))) to measure the distance between the source feature and the pseudo-target feature, and then combine the error to optimize the source feature to the target feature space
  • the mapping ;
  • Step S35 repeat the mapping step, the distinguishing step and the optimization step until the source domain and the target domain are adapted to obtain the common feature parameters; among them, the source domain and the target domain are adapted to each other, that is, the error of the loss function calculation is less than the set Threshold; the smaller the error, the closer the source domain to the target domain, the better the migration effect;
  • Step S36 Migration step: Migrate the general feature parameters to the second face beauty prediction model.
  • the confrontation network is used to reduce the distribution difference between the source domain and the target domain, that is, the distribution difference between the first face beauty prediction model and the second face beauty prediction model; to achieve the purpose of knowledge transfer and reuse from the source domain to the target domain.
  • the overall migration of the general feature parameters of the first face beauty prediction model to the second face beauty prediction model is specifically as follows: each of the first feature sharing layer 12, the first independent feature extraction layer 13, and the first classification layer 14 The parameters are correspondingly migrated to the second feature sharing layer 22, the second independent feature extraction layer 23, and the second classification layer 25; the entire second face beauty prediction model accepts the parameters of the migration learning, and the overall model is optimized.
  • the above face beauty prediction method measures the similarity of multiple auxiliary tasks, selects the auxiliary tasks with high similarity to the main task, builds a pre-training network model based on this, and transfers the parameters of the pre-trained network model to the main task face
  • the network model of the main task is optimized to avoid the negative transfer caused by useless parameters caused by the training of irrelevant auxiliary tasks, which can greatly reduce the amount of training, improve the efficiency of classification and recognition, and improve the accuracy of classification and recognition.
  • an apparatus for predicting face beauty based on anti-transfer learning, applying the above-mentioned face beauty prediction method includes:
  • the similarity measurement module 100 is used to measure the similarity between N auxiliary tasks and the main task to obtain A auxiliary tasks with the highest similarity, where the main task is the task of predicting the beauty of the face, and the auxiliary task is the task of identifying the factors of the beauty of the face , N>A;
  • the first model building module 210 is used to build A first face beauty prediction models corresponding to A auxiliary tasks with the highest similarity;
  • the second model building module 220 is used to build a second face beauty prediction model used for face beauty prediction
  • the parameter migration module 300 is configured to use A of the first face beauty prediction model as the source domain and the second face beauty prediction model as the target domain to find the common features of the source domain relative to the target domain through adversarial network pre-training Parameters, transferring the general feature parameters to the second face beauty prediction model;
  • the calculation module 400 is used to input the face image to be tested to the second face beauty prediction model that is retrained to output the face beauty prediction result.
  • the similarity measurement module is used to find the most relevant among the auxiliary tasks of identifying face factors, and to construct the first face beauty prediction model for pre-training; reducing the training cost of pre-training , To reduce the bias caused by the auxiliary tasks with irrelevant factors to the first face beauty prediction model, and avoid negative migration.
  • the parameter migration module 300 migrates the general feature parameters formed after pre-training to the second face beauty prediction model, and realizes the final face beauty prediction, reduces the calculation amount through migration learning, compresses the training time, and reaches the calculation module 400 to use less The training images to obtain a more accurate model effect.
  • the similarity measurement module 100 includes:
  • the feature expression acquisition module 110 is used to construct a fully-supervised specific network for the N auxiliary tasks and the main task respectively and perform training to obtain the feature expression E s (I) of each task;
  • the tightness measurement module 120 is used to construct a migration network between N auxiliary tasks and the main task, and measure the task tightness between the N auxiliary tasks and the main task.
  • the calculation method of the task tightness is: Where I is the input, D is the data set, f t (I) is the true value of the t-th input I, L t is the loss between the true value and the predicted value, and E I ⁇ D represents the expected value;
  • the normalization processing module 130 is used to normalize the loss of the migration network through the analytic hierarchy process to obtain an incidence matrix
  • the optimization processing module 140 is used for optimizing the incidence matrix to obtain A auxiliary tasks with the highest similarity.
  • the first face beauty prediction model includes a first preprocessing layer 11 for preprocessing face images, a first feature sharing layer 12 for extracting shared image features, and a first feature sharing layer 12 for extracting features from the shared image.
  • the second face beauty prediction model includes a second preprocessing layer 21, a second feature sharing layer 22, and a second independent feature extraction layer 23 connected in sequence ,
  • a feature fusion layer 24 and a second classification layer 25 used to fuse independent features and geometric features and texture features of the corresponding facial beauty prediction task.
  • the parameter migration module 300 includes:
  • the mapping module 330 is used to map the source feature to the target feature space to obtain the pseudo target feature T(G(x s ));
  • the distinguishing module 340 is used to distinguish the source of the target feature and the pseudo-target feature and calculate the error through the loss function;
  • the optimization module 350 is configured to use the regularization term r(G(x s ), T(G(x s ))) to measure the distance between the source feature and the pseudo target feature, and then combine the error to optimize the source feature to the target feature space
  • the mapping ;
  • the parameter acquisition module 360 is used to acquire general characteristic parameters when both the source domain and the target domain are adapted;
  • the migration sub-module 370 is configured to migrate the general feature parameters to the second face beauty prediction model.
  • the parameter migration module 300 correspondingly migrates the respective parameters of the first feature sharing layer 12, the first independent feature extraction layer 13, and the first classification layer 14 to the second feature sharing layer 22, the second independent feature extraction layer 23, and the second feature sharing layer.
  • Classification layer 25 the respective parameters of the first feature sharing layer 12, the first independent feature extraction layer 13, and the first classification layer 14 to the second feature sharing layer 22, the second independent feature extraction layer 23, and the second feature sharing layer.
  • the above-mentioned facial beauty prediction device measures the similarity of multiple auxiliary tasks, selects the auxiliary tasks with high similarity to the main task, and builds a parameter migration network model based on the confrontation network based on this, and transfers the parameters to the general features generated by the network model
  • the parameters are migrated to the main task face beauty recognition network model, so that the main task network model is optimized, and the negative transfer caused by useless parameters caused by the training of irrelevant auxiliary tasks can be avoided, which can greatly reduce the amount of training and improve the efficiency of classification and recognition. Improve classification and recognition accuracy.
  • Another embodiment of the present invention provides a storage medium that stores executable instructions, and the executable instructions enable a processor connected to the storage medium to perform facial beauty prediction methods based on the above-mentioned anti-migration learning-based face beauty prediction method.
  • the image is processed to obtain the beautiful face recognition result.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

L'invention concerne un procédé et un dispositif de prédiction de beauté faciale basée sur un apprentissage par transfert antagoniste, le procédé comprenant les étapes suivantes consistant à : sélectionner les tâches auxiliaires les plus pertinentes parmi une pluralité de tâches auxiliaires de reconnaissance de facteur facial au moyen d'une mesure de similitude, et sur la base de celles-ci, construire un premier modèle de prédiction de beauté faciale ; transférer des paramètres de caractéristiques générales formés après un pré-apprentissage d'un réseau antagoniste vers un second modèle de prédiction de beauté faciale ; et entrer une image faciale à mesurer pour effectuer une reconnaissance. Le présent procédé réduit le coût d'apprentissage d'un pré-apprentissage, réduit le transfert négatif dû à des tâches auxiliaires ayant des facteurs non apparentés, et réduit également la complexité de calcul pour ré-entraîner le second modèle de prédiction de beauté faciale, de telle sorte qu'un modèle plus précis est obtenu en utilisant moins d'images d'apprentissage.
PCT/CN2020/112528 2019-09-20 2020-08-31 Procédé et dispositif de prédiction de beauté faciale basée sur un apprentissage par transfert antagoniste WO2021052159A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910893810.7 2019-09-20
CN201910893810.7A CN110705406B (zh) 2019-09-20 2019-09-20 基于对抗迁移学习的人脸美丽预测方法及装置

Publications (1)

Publication Number Publication Date
WO2021052159A1 true WO2021052159A1 (fr) 2021-03-25

Family

ID=69195631

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/112528 WO2021052159A1 (fr) 2019-09-20 2020-08-31 Procédé et dispositif de prédiction de beauté faciale basée sur un apprentissage par transfert antagoniste

Country Status (2)

Country Link
CN (1) CN110705406B (fr)
WO (1) WO2021052159A1 (fr)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113128113A (zh) * 2021-04-14 2021-07-16 国网上海市电力公司 一种基于深度学习和迁移学习的贫乏信息建筑负荷预测方法
CN114444374A (zh) * 2021-11-29 2022-05-06 河南工业大学 一种基于相似性度量的多源到多目标域自适应的方法
CN114898424A (zh) * 2022-04-01 2022-08-12 中南大学 一种基于双重标签分布的轻量化人脸美学预测方法
CN115879008A (zh) * 2023-03-02 2023-03-31 中国空气动力研究与发展中心计算空气动力研究所 一种数据融合模型训练方法、装置、设备及存储介质
WO2023236594A1 (fr) * 2022-06-09 2023-12-14 五邑大学 Procédé et appareil de prédiction de beauté de visage, dispositif électronique et support de stockage

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110705406B (zh) * 2019-09-20 2022-11-15 五邑大学 基于对抗迁移学习的人脸美丽预测方法及装置
CN111382846B (zh) * 2020-05-28 2020-09-01 支付宝(杭州)信息技术有限公司 基于迁移学习的训练神经网络模型的方法和装置
CN111784596A (zh) * 2020-06-12 2020-10-16 北京理工大学 基于生成对抗神经网络的通用内窥镜图像增强方法及装置
CN111832435A (zh) 2020-06-24 2020-10-27 五邑大学 基于迁移与弱监督的美丽预测方法、装置及存储介质
CN111914908B (zh) * 2020-07-14 2023-10-24 浙江大华技术股份有限公司 一种图像识别模型训练方法、图像识别方法及相关设备
CN112069916B (zh) * 2020-08-14 2024-02-20 五邑大学 人脸美丽预测方法、装置、系统及可读存储介质
CN112069946B (zh) * 2020-08-25 2024-02-20 五邑大学 人脸美丽预测方法、装置、系统及存储介质
CN113450267B (zh) * 2021-05-14 2022-08-19 桂林电子科技大学 可快速获取多种自然退化图像复原模型的迁移学习方法
CN114548382B (zh) * 2022-04-25 2022-07-15 腾讯科技（深圳）有限公司 迁移训练方法、装置、设备、存储介质及程序产品

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6826300B2 (en) * 2001-05-31 2004-11-30 George Mason University Feature based classification
CN108959522A (zh) * 2018-04-26 2018-12-07 浙江工业大学 基于半监督对抗生成网络的迁移检索方法
CN110119689A (zh) * 2019-04-18 2019-08-13 五邑大学 一种基于多任务迁移学习的人脸美丽预测方法
CN110705406A (zh) * 2019-09-20 2020-01-17 五邑大学 基于对抗迁移学习的人脸美丽预测方法及装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10719742B2 (en) * 2018-02-15 2020-07-21 Adobe Inc. Image composites using a generative adversarial neural network
CN109523018B (zh) * 2019-01-08 2022-10-18 重庆邮电大学 一种基于深度迁移学习的图片分类方法
CN109948648B (zh) * 2019-01-31 2023-04-07 中山大学 一种基于元对抗学习的多目标域适应迁移方法及系统
CN110084121A (zh) * 2019-03-27 2019-08-02 南京邮电大学 基于谱归一化的循环生成式对抗网络的人脸表情迁移的实现方法
CN110210486B (zh) * 2019-05-15 2021-01-01 西安电子科技大学 一种基于素描标注信息的生成对抗迁移学习方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6826300B2 (en) * 2001-05-31 2004-11-30 George Mason University Feature based classification
CN108959522A (zh) * 2018-04-26 2018-12-07 浙江工业大学 基于半监督对抗生成网络的迁移检索方法
CN110119689A (zh) * 2019-04-18 2019-08-13 五邑大学 一种基于多任务迁移学习的人脸美丽预测方法
CN110705406A (zh) * 2019-09-20 2020-01-17 五邑大学 基于对抗迁移学习的人脸美丽预测方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
甘俊英 等 (GAN, JUNYING ET AL.): "基于双激活层深度卷积特征的人脸美丽预测研究 (Research of Facial Beauty Prediction Based on Deep Convolutional Features Using Double Activation Layer)", 电子学报 (ACTA ELECTRONICA SINICA), vol. 47, no. 3, 31 March 2019 (2019-03-31), XP055772289, ISSN: 0372-2112, DOI: 10.3969/j.issn.0372-2112.2019.03.017 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113128113A (zh) * 2021-04-14 2021-07-16 国网上海市电力公司 一种基于深度学习和迁移学习的贫乏信息建筑负荷预测方法
CN113128113B (zh) * 2021-04-14 2024-04-12 国网上海市电力公司 一种基于深度学习和迁移学习的贫乏信息建筑负荷预测方法
CN114444374A (zh) * 2021-11-29 2022-05-06 河南工业大学 一种基于相似性度量的多源到多目标域自适应的方法
CN114898424A (zh) * 2022-04-01 2022-08-12 中南大学 一种基于双重标签分布的轻量化人脸美学预测方法
CN114898424B (zh) * 2022-04-01 2024-04-26 中南大学 一种基于双重标签分布的轻量化人脸美学预测方法
WO2023236594A1 (fr) * 2022-06-09 2023-12-14 五邑大学 Procédé et appareil de prédiction de beauté de visage, dispositif électronique et support de stockage
CN115879008A (zh) * 2023-03-02 2023-03-31 中国空气动力研究与发展中心计算空气动力研究所 一种数据融合模型训练方法、装置、设备及存储介质
CN115879008B (zh) * 2023-03-02 2023-05-26 中国空气动力研究与发展中心计算空气动力研究所 一种数据融合模型训练方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN110705406B (zh) 2022-11-15
CN110705406A (zh) 2020-01-17

Similar Documents

Publication Publication Date Title
WO2021052159A1 (fr) Procédé et dispositif de prédiction de beauté faciale basée sur un apprentissage par transfert antagoniste
RU2770752C1 (ru) Способ и устройство для обучения модели распознавания лица и устройство для определения ключевой точки лица
WO2021083241A1 (fr) Procédé d'évaluation de qualité d'image faciale, procédé d'apprentissage de modèle d'extraction de caractéristique, système de traitement d'image, support lisible par ordinateur et terminal de communication sans fil
CN108171209B (zh) 一种基于卷积神经网络进行度量学习的人脸年龄估计方法
US11809485B2 (en) Method for retrieving footprint images
WO2020228446A1 (fr) Procédé et appareil d'entraînement de modèles, et terminal et support de stockage
CN111126482B (zh) 一种基于多分类器级联模型的遥感影像自动分类方法
WO2021052160A1 (fr) Procédé de prédiction de beauté de visage sur la base d'une migration multitâches et dispositif
CN110796018B (zh) 一种基于深度图像和彩色图像的手部运动识别方法
WO2022257487A1 (fr) Procédé et appareil d'apprentissage de modèle d'estimation de profondeur, dispositif électronique et support de stockage
CN111783532B (zh) 一种基于在线学习的跨年龄人脸识别方法
CN111062423B (zh) 基于自适应特征融合的点云图神经网络的点云分类方法
CN111401219B (zh) 一种手掌关键点检测方法和装置
CN111127360A (zh) 一种基于自动编码器的灰度图像迁移学习方法
WO2023231753A1 (fr) Procédé d'apprentissage de réseau neuronal, procédé de traitement de données et dispositif
CN114677339A (zh) 一种引入注意力机制的输电线路螺栓脱销缺陷检测方法
CN117437522B (zh) 一种人脸识别模型训练方法、人脸识别方法及装置
CN111126155A (zh) 一种基于语义约束生成对抗网络的行人再识别方法
CN113221695A (zh) 训练肤色识别模型的方法、识别肤色的方法及相关装置
CN116977271A (zh) 缺陷检测方法、模型训练方法、装置及电子设备
CN114445875A (zh) 基于深度学习的身份识别与人脸比对系统及训练方法
CN113255701B (zh) 一种基于绝对-相对学习架构的小样本学习方法和系统
JP2020064364A (ja) 学習装置、画像生成装置、学習方法、及び学習プログラム
CN114639132A (zh) 人脸识别场景下的特征提取模型处理方法、装置、设备
CN109829898B (zh) 一种用于互联网检测中基于神经网络的测量检测系统及方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20864493

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20864493

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20864493

Country of ref document: EP

Kind code of ref document: A1