CN113656632B - Attribute-aware Hash coding learning method in large-scale fine-grained image retrieval - Google Patents

Attribute-aware Hash coding learning method in large-scale fine-grained image retrieval Download PDF

Info

Publication number
CN113656632B
CN113656632B CN202111223861.2A CN202111223861A CN113656632B CN 113656632 B CN113656632 B CN 113656632B CN 202111223861 A CN202111223861 A CN 202111223861A CN 113656632 B CN113656632 B CN 113656632B
Authority
CN
China
Prior art keywords
hash
image
attribute
feature
dimension
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.)
Active
Application number
CN202111223861.2A
Other languages
Chinese (zh)
Other versions
CN113656632A (en
Inventor
魏秀参
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.)
Nanjing University of Science and Technology
Original Assignee
Nanjing University of Science and Technology
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 Nanjing University of Science and Technology filed Critical Nanjing University of Science and Technology
Priority to CN202111223861.2A priority Critical patent/CN113656632B/en
Publication of CN113656632A publication Critical patent/CN113656632A/en
Application granted granted Critical
Publication of CN113656632B publication Critical patent/CN113656632B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06N3/088—Non-supervised learning, e.g. competitive learning

Abstract

The invention discloses an attribute perception hash coding learning method in large-scale fine-grained image retrieval, which comprises the following steps: extracting global feature and local feature information in the image through a convolutional neural network; the method comprises the steps of constructing a Hash learning module, extracting high-dimensional image feature information to a low-dimensional Hash space, constructing a Hash feature decoder, and guiding an attribute feature extraction mode in the Hash learning process in an unsupervised mode; the identification capability of each dimension attribute obtained by learning of the Hash module is enhanced, and the redundant correlation among the attribute features of each dimension is removed, so that the attribute features of each dimension have unique and complete expression meanings. The method extracts local and global features in the image through a convolutional neural network and an attention mechanism, guides Hash learning to keep relatively complete and important overall image feature information by establishing an attribute feature decoder and enabling feature vectors to have self-orthogonality characteristics, and can obtain higher image retrieval accuracy.

Description

Attribute-aware Hash coding learning method in large-scale fine-grained image retrieval
Technical Field
The invention belongs to the field of computer vision, and particularly relates to an attribute perception hash coding learning method in large-scale fine-grained image retrieval.
Background
Fine-grained image retrieval has gained increasing attention in recent years as an important component of fine-grained image analysis. The fine-grained image recognition is a basic research subject in the field of computer vision and pattern recognition, and aims to research the visual recognition task of different subclasses of fine-grained levels under a certain traditional semantic class, for example, … … fine-grained image recognition of dogs of different subclasses, birds of different subclasses, automobiles of different vehicle types and the like is called as 'visual perception embedded basic stone work' by the international authority scholars of computer vision, ICCV Helmholtz awards and the professor that Marr awards the Serge Belongie. The object objects in the fine-grained image have only slight visual difference in the difference between classes, but have larger variation in the differences in the classes such as posture, scale and the like, so that the retrieval difficulty is higher.
Hash learning is a method for mapping data into a binary string form by a machine learning method, and can remarkably reduce the storage and communication overhead of the data, thereby effectively improving the efficiency of a learning system. The purpose of hash learning is to learn a binary hash code representation of data, so that the hash code retains the neighbor relation in the original space as much as possible, i.e., retains similarity. Specifically, each data point would be encoded by a compact binary string, and two similar points in the original space should be mapped to two similar points in the hash space. Hash methods are roughly classified into two types, namely, data-independent methods and data-dependent methods. In a data-independent hashing approach, the hash function in the model is typically generated randomly and independent of any training data, but the improvement in retrieval performance requires trading for the length of the hash code. Data-dependent hashing methods attempt to learn a hash function from some training data, known as the learning hash algorithm. Compared with a data-independent method, the learning hash algorithm can achieve higher accuracy with shorter hash codes. Therefore, learning hash algorithms is more popular than data-independent methods in practical applications. With the rise of deep learning, some learning hash methods integrate deep feature learning into a hash frame, and obtain good performance. In past work, many deep hash methods have been proposed for large-scale image retrieval. Compared with a deep unsupervised hash method, the deep supervised hash method can fully mine semantic information and obtain higher retrieval precision.
Although the current deep learning hash algorithm has good retrieval effect, the deep learning hash algorithm is limited to coarse-grained data retrieval. In many cases, taking a picture search of a dog as an example, one would not only want to search for a dog but not other animals, but what breed of dog it is, such as Cork or Samoyaer. In such a case, the retrieval accuracy of the currently-available learning hash method is very low. On the other hand, the binary code obtained by the existing learning hash method has no practical significance, so that the storage and retrieval results of the pictures do not have any interpretability. Therefore, a new learning hash method with practical meaning that can obtain a response result with high accuracy in a fine-grained retrieval environment is needed.
Disclosure of Invention
The invention aims to provide an attribute perception hash coding learning method in large-scale fine-grained image retrieval.
The technical scheme for realizing the purpose of the invention is as follows: an attribute perception hash coding learning method in large-scale fine-grained image retrieval comprises the following steps:
step 1, extracting global feature and local feature information in an image through a convolutional neural network;
Step 2, constructing a Hash learning module, extracting high-dimensional image feature information into a low-dimensional Hash space, constructing a Hash feature decoder, and guiding an attribute feature extraction mode in the Hash learning process in an unsupervised mode;
and 3, enhancing the identification capability of each dimension attribute obtained by learning of the Hash module in the step 2, and removing the redundant correlation among the features of each dimension attribute.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above-mentioned attribute-aware hash-code learning method in large-scale fine-grained image retrieval when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described attribute-aware hash-code learning method in large-scale fine-grained image retrieval.
Compared with the prior art, the invention has the remarkable advantages that: (1) the method has the performance result of the traditional Hash learning method compared with the coarse-grained image retrieval, and has the retrieval accuracy rate far exceeding that of the traditional Hash learning method in the fine-grained image retrieval; (2) establishing an attribute feature decoder, and guiding Hash learning to reserve relatively complete and important integral image feature information, so that the information contained in the original image can be more comprehensively expressed after information features in each dimension of Hash space are recombined; (3) by constructing the attribute self-orthogonality mode, the redundancy correlation of the attribute features learned by each dimension space is eliminated, so that the attribute features of each dimension have unique and complete expression meanings, namely each hash dimension can represent attribute feature information of a depth. The invention gives attribute meaning to each dimension of information in the hash space, which is not possessed by other hash learning methods.
Drawings
Fig. 1 is a schematic diagram of an attribute-aware hash coding learning method in large-scale fine-grained image retrieval according to the present invention.
Detailed Description
With reference to fig. 1, a method for learning attribute-aware hash codes in large-scale fine-grained image retrieval specifically includes the following steps:
step 1, extracting global feature and local feature information in an image through a convolutional neural network;
attention plays a very important role in human perception, and let us pay attention to the salient features of the same thing or scene, so we introduce an attention mechanism in a convolutional neural network to acquire global and local features of an image to better express the salient features of each image. Specifically, it is first necessary to extract an input image by a convolutional neural network
Figure 581165DEST_PATH_IMAGE001
The depth characteristics of (a):
Figure 942263DEST_PATH_IMAGE002
wherein
Figure 100712DEST_PATH_IMAGE003
Represents a custom convolutional neural network that is,C、HandWrespectively representing depth characteristics
Figure 874633DEST_PATH_IMAGE004
The number of channels, the characteristic length and the characteristic width; depth feature obtained in equation (1)
Figure 739821DEST_PATH_IMAGE004
On the basis of (1), introduceCA local attention guidance module, hereinCLocal attention guidance module and depth feature
Figure 940995DEST_PATH_IMAGE004
Number of channelsCIs correspondingly marked as
Figure 649057DEST_PATH_IMAGE005
A global attention guidance module is introduced, and is recorded as
Figure 226669DEST_PATH_IMAGE006
And outputting the local characteristics of the image as follows:
Figure 277189DEST_PATH_IMAGE007
the global feature output of the image is:
Figure 649264DEST_PATH_IMAGE008
obtaining a global feature vector of the image by performing global average pooling on the feature outputs
Figure 516726DEST_PATH_IMAGE009
And local depth feature vector
Figure 632450DEST_PATH_IMAGE010
And recording the integral characteristic vector of the image obtained after sequential splicing as
Figure 534547DEST_PATH_IMAGE011
。
Step 2, constructing a Hash learning module, extracting high-dimensional image feature information into a low-dimensional Hash space, constructing a Hash feature decoder, and guiding an attribute feature extraction mode in the Hash learning process in an unsupervised mode;
the Hash learning module passes through a transformation matrix
Figure 749627DEST_PATH_IMAGE012
The depth feature vector obtained in the step 1 is processed
Figure 963440DEST_PATH_IMAGE011
Mapping into a k-dimensional Hash space, denoted
Figure 351696DEST_PATH_IMAGE013
. Binary hash coding of images
Figure 388527DEST_PATH_IMAGE014
By
Figure 102405DEST_PATH_IMAGE013
Obtained by two activations:
Figure 944459DEST_PATH_IMAGE015
wherein
Figure 401985DEST_PATH_IMAGE013
Is an approximate binary code of dimension k by transforming matrices
Figure 950778DEST_PATH_IMAGE012
The obtained highly condensed image feature expression vector,
Figure 835558DEST_PATH_IMAGE014
the binary coding of the finally obtained image is performed, that is, the information of the whole image can be expressed by the bit information of k bits, and the retrieval space is greatly compressed. First activating tanh to constrain
Figure 164908DEST_PATH_IMAGE013
The gradient can be reversely propagated, and the second activation restricts the characteristic vector to Hamming coding to accelerate the image retrieval speed.
When calculating hash loss, it is assumed thatnA query point
Figure 426125DEST_PATH_IMAGE016
Andmindividual database point
Figure 157321DEST_PATH_IMAGE017
Following equation (4), the hash codes of the query point and the database point can be respectively expressed as:
Figure 215931DEST_PATH_IMAGE018
Figure 360473DEST_PATH_IMAGE019
wherein
Figure 425381DEST_PATH_IMAGE014
Is through a query point
Figure 11084DEST_PATH_IMAGE020
The resulting hash-code is activated and,
Figure 237666DEST_PATH_IMAGE021
is through database points
Figure 541608DEST_PATH_IMAGE022
The resulting hash code is activated. The loss of hash coding can be noted as:
Figure 144628DEST_PATH_IMAGE023
wherein
Figure 853345DEST_PATH_IMAGE024
，
Figure 516408DEST_PATH_IMAGE025
。
The characteristic decoder reconstructs the hash space characteristic after tanh activation
Figure 42067DEST_PATH_IMAGE013
Restoring the attribute features and constraining the feature loss, and recording as:
Figure 448777DEST_PATH_IMAGE026
wherein the content of the first and second substances,
Figure 743493DEST_PATH_IMAGE027
d represents each feature vector
Figure 780719DEST_PATH_IMAGE011
Dimension (d);
Figure 793674DEST_PATH_IMAGE028
representing a reconstruction matrix, being a Hash transform matrix
Figure 738496DEST_PATH_IMAGE012
Transposing;
Figure 156227DEST_PATH_IMAGE029
，
Figure 957830DEST_PATH_IMAGE030
is composed of
Figure 458081DEST_PATH_IMAGE031
The hyper-parameters introduced in the loss optimization process,
Figure 206594DEST_PATH_IMAGE032
through unsupervised coding reconstruction, Hash learning can be guided to keep relatively complete and important overall image characteristic information, and information contained in the original image can be more comprehensively expressed after information characteristics in each dimension of Hash space are recombined.
And 3, enhancing the identification capability of each dimension attribute obtained by learning of the Hash module in the step 2, and removing the redundant correlation among the features of each dimension attribute.
Performing hash transformation on the characteristic vector obtained in the step 2 and performing tanh activation on the characteristic vector
Figure 679164DEST_PATH_IMAGE033
Constructing self-orthogonality loss, and recording as:
Figure 854930DEST_PATH_IMAGE034
wherein
Figure 842478DEST_PATH_IMAGE035
The hash dimension is an identity matrix, so that the redundant correlation of the attribute features learned by each dimension space can be eliminated, the attribute features of each dimension have unique and complete expression meanings, and each hash dimension can represent attribute feature information of a depth.
The overall constraint penalty can be written as:
Figure 925840DEST_PATH_IMAGE036
Figure 306444DEST_PATH_IMAGE037
（10）
wherein
Figure 387533DEST_PATH_IMAGE038
And
Figure 862377DEST_PATH_IMAGE039
for the introduced hyper-parameters, for the alignment dimension.
The binary hash-coded output of the input image can be written as:
Figure 687113DEST_PATH_IMAGE040
in the formulaGAP(
Figure 931013DEST_PATH_IMAGE041
) Representing the global average pooling.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (3)

1. An attribute perception hash coding learning method in large-scale fine-grained image retrieval comprises the following steps:
Step 1, extracting global feature and local feature information in an image through a convolutional neural network; the method comprises the following specific steps:
by introducing an attention mechanism into the convolutional neural network, acquiring global and local features of the image to express a salient feature of each image;
firstly, an input image is extracted through a convolutional neural network
Figure 284691DEST_PATH_IMAGE001
The depth characteristics of (a):
Figure 39020DEST_PATH_IMAGE002
wherein
Figure 995606DEST_PATH_IMAGE003
Represents a custom convolutional neural network that is,C、HandWrespectively representing depth characteristics
Figure 518991DEST_PATH_IMAGE004
The number of channels, the characteristic length and the characteristic width; depth feature obtained in equation (1)
Figure 417677DEST_PATH_IMAGE004
On the basis of (1), introduceCA local injectionThe guiding module of the intention is recorded as
Figure 659303DEST_PATH_IMAGE005
A global attention guidance module is introduced, and is recorded as
Figure 403268DEST_PATH_IMAGE006
And the local feature output of the image is as follows:
Figure 46739DEST_PATH_IMAGE007
the global feature output of the image is:
Figure 850747DEST_PATH_IMAGE008
obtaining a global feature vector of the image by performing global average pooling on the feature outputs
Figure 579668DEST_PATH_IMAGE009
And local depth feature vector
Figure 658483DEST_PATH_IMAGE010
And recording the integral characteristic vector of the image obtained after sequential splicing as
Figure 874569DEST_PATH_IMAGE011
；
Step 2, constructing a Hash learning module, extracting high-dimensional image feature information into a low-dimensional Hash space, constructing a Hash feature decoder, and guiding an attribute feature extraction mode in the Hash learning process in an unsupervised mode, namely guiding Hash learning to keep the whole image feature information so that the information contained in the original image can be expressed after information features in each dimension of Hash space are recombined; the method specifically comprises the following steps:
Constructing a Hash learning module by a transformationMatrix of
Figure 646216DEST_PATH_IMAGE012
Integrating the integral characteristic vector obtained in the step 1
Figure 65696DEST_PATH_IMAGE011
Mapping into a k-dimensional Hash space, denoted
Figure 948202DEST_PATH_IMAGE013
(ii) a Binary hash coding of images
Figure 769527DEST_PATH_IMAGE014
By
Figure 712075DEST_PATH_IMAGE013
Obtained by two activations:
Figure 618851DEST_PATH_IMAGE015
wherein
Figure 39469DEST_PATH_IMAGE016
Is an approximate binary code of dimension k by transforming matrices
Figure 728682DEST_PATH_IMAGE012
The obtained image characteristic expression vector is used for expressing the image characteristic,
Figure 842132DEST_PATH_IMAGE014
then, the binary coding of the finally obtained image is performed, namely the information of the whole image is expressed by the bit information of k bits; first activating tanh to constrain
Figure 767363DEST_PATH_IMAGE013
The gradient can be propagated reversely, and the second activation restricts the characteristic vector to Hamming coding;
when calculating hash loss, it is assumed thatnA query point
Figure 460512DEST_PATH_IMAGE017
Andmindividual database point
Figure 522009DEST_PATH_IMAGE018
Following equation (4), the hash codes of the query point and the database point are respectively recorded as:
Figure 275201DEST_PATH_IMAGE019
Figure 687728DEST_PATH_IMAGE020
wherein
Figure 715727DEST_PATH_IMAGE021
Is through a query point
Figure 366151DEST_PATH_IMAGE022
The resulting hash-code is activated and,
Figure 555824DEST_PATH_IMAGE023
is through database points
Figure 173756DEST_PATH_IMAGE024
Activating the obtained hash code; the loss of hash coding is noted as:
Figure 739867DEST_PATH_IMAGE025
wherein
Figure 510377DEST_PATH_IMAGE026
，
Figure 870951DEST_PATH_IMAGE027
；
The characteristic decoder reconstructs the hash space characteristic after tanh activation
Figure 726911DEST_PATH_IMAGE013
Restoring the attribute features and constraining the feature loss, and recording as:
Figure 96713DEST_PATH_IMAGE028
wherein the content of the first and second substances,
Figure 987308DEST_PATH_IMAGE029
，drepresenting each feature vector
Figure 253205DEST_PATH_IMAGE011
Dimension (d);
Figure 862041DEST_PATH_IMAGE030
Representing a reconstruction matrix, being a Hash transform matrix
Figure 255107DEST_PATH_IMAGE012
Transposing;
Figure 265788DEST_PATH_IMAGE031
is composed of
Figure 702586DEST_PATH_IMAGE032
The hyper-parameters introduced in the loss optimization process,
Figure 798718DEST_PATH_IMAGE033
，
Figure 510322DEST_PATH_IMAGE034
；
step 3, enhancing the identification capability of each dimension attribute obtained by the Hash learning module in the step 2, and removing redundant correlation among the attribute features of each dimension in a mode of constructing attribute self-orthogonality, so that the attribute features of each dimension have unique and complete expression meanings, namely each Hash dimension can represent attribute feature information of one depth; the method specifically comprises the following steps:
enhancing the identification capability of each dimension attribute obtained by the Hash learning module in the step 2, and performing hash transformation on the matrix in the step 2 and performing tanh activation on the obtained feature vector set
Figure 844351DEST_PATH_IMAGE035
Constructing self-orthogonality loss, and recording as:
Figure 983209DEST_PATH_IMAGE036
wherein
Figure 35478DEST_PATH_IMAGE037
The unit matrix is used, so that the redundant correlation of the attribute characteristics learned by each dimension space can be eliminated;
the overall constraint loss is noted as:
Figure 285194DEST_PATH_IMAGE038
Figure 988577DEST_PATH_IMAGE039
（10）
wherein
Figure 298335DEST_PATH_IMAGE040
And
Figure 369059DEST_PATH_IMAGE041
for the introduced hyper-parameters, for the alignment dimension;
the binary hash-coded output of the input image is noted as:
Figure 891308DEST_PATH_IMAGE042
in the formulaGAP(
Figure 731088DEST_PATH_IMAGE043
) Representing the global average pooling, which has the effect of reducing the dimension of the feature map and forming a feature point.
2. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program performs the steps of the attribute-aware hash-code learning method in large-scale fine-grained image retrieval according to claim 1.
3. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of attribute-aware hash-code learning in large-scale fine-grained image retrieval as set forth in claim 1.
CN202111223861.2A 2021-10-21 2021-10-21 Attribute-aware Hash coding learning method in large-scale fine-grained image retrieval Active CN113656632B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111223861.2A CN113656632B (en) 2021-10-21 2021-10-21 Attribute-aware Hash coding learning method in large-scale fine-grained image retrieval

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111223861.2A CN113656632B (en) 2021-10-21 2021-10-21 Attribute-aware Hash coding learning method in large-scale fine-grained image retrieval

Publications (2)

Publication Number Publication Date
CN113656632A CN113656632A (en) 2021-11-16
CN113656632B true CN113656632B (en) 2022-08-12

Family

ID=78484339

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111223861.2A Active CN113656632B (en) 2021-10-21 2021-10-21 Attribute-aware Hash coding learning method in large-scale fine-grained image retrieval

Country Status (1)

Country Link
CN (1) CN113656632B (en)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110069644B (en) * 2019-04-24 2023-06-06 南京邮电大学 Compressed domain large-scale image retrieval method based on deep learning
CN111125411B (en) * 2019-12-20 2022-06-21 昆明理工大学 Large-scale image retrieval method for deep strong correlation hash learning

Also Published As

Publication number Publication date
CN113656632A (en) 2021-11-16

Similar Documents

Publication Publication Date Title
Guo et al. Locally supervised deep hybrid model for scene recognition
CN111079532B (en) Video content description method based on text self-encoder
Taylor et al. Learning invariance through imitation
Jiang et al. Cascaded subpatch networks for effective CNNs
CN111723220A (en) Image retrieval method and device based on attention mechanism and Hash and storage medium
Mathur et al. Camera2Caption: a real-time image caption generator
CN111666588B (en) Emotion differential privacy protection method based on generation countermeasure network
CN111400494B (en) Emotion analysis method based on GCN-Attention
CN114896434B (en) Hash code generation method and device based on center similarity learning
Dixit et al. Object based scene representations using fisher scores of local subspace projections
Xie et al. Feature normalization for part-based image classification
CN111325766A (en) Three-dimensional edge detection method and device, storage medium and computer equipment
CN113961736A (en) Method and device for generating image by text, computer equipment and storage medium
CN113780249B (en) Expression recognition model processing method, device, equipment, medium and program product
CN115565238A (en) Face-changing model training method, face-changing model training device, face-changing model training apparatus, storage medium, and program product
CN116229531A (en) Face front image synthesis method for collaborative progressive generation countermeasure network
CN114283352A (en) Video semantic segmentation device, training method and video semantic segmentation method
Robert The Role of Deep Learning in Computer Vision
CN113656632B (en) Attribute-aware Hash coding learning method in large-scale fine-grained image retrieval
CN114399646B (en) Image description method and device based on transform structure
CN111611427B (en) Image retrieval method and system based on linear discriminant analysis depth hash algorithm
CN115457374A (en) Deep pseudo-image detection model generalization evaluation method and device based on reasoning mode
CN114612826A (en) Video and text similarity determination method and device, electronic equipment and storage medium
Li et al. A semi-supervised learning model based on convolutional autoencoder and convolutional neural network for image classification
KR102592515B1 (en) Apparatus and method for embedding-based data set processing

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
GR01 Patent grant
GR01 Patent grant