CN110516092B - Automatic image annotation method based on K nearest neighbor and random walk algorithm - Google Patents

Automatic image annotation method based on K nearest neighbor and random walk algorithm Download PDF

Info

Publication number
CN110516092B
CN110516092B CN201910822291.5A CN201910822291A CN110516092B CN 110516092 B CN110516092 B CN 110516092B CN 201910822291 A CN201910822291 A CN 201910822291A CN 110516092 B CN110516092 B CN 110516092B
Authority
CN
China
Prior art keywords
image
probability
label
prediction
vector
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
CN201910822291.5A
Other languages
Chinese (zh)
Other versions
CN110516092A (en
Inventor
王振武
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.)
China University of Mining and Technology Beijing CUMTB
Original Assignee
China University of Mining and Technology Beijing CUMTB
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 China University of Mining and Technology Beijing CUMTB filed Critical China University of Mining and Technology Beijing CUMTB
Priority to CN201910822291.5A priority Critical patent/CN110516092B/en
Publication of CN110516092A publication Critical patent/CN110516092A/en
Application granted granted Critical
Publication of CN110516092B publication Critical patent/CN110516092B/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
    • G06F16/53—Querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks

Abstract

The invention provides an automatic image labeling method based on K neighbor and random walk algorithm, belonging to the field of image retrieval. The method is characterized in that a vertex set of a probability graph model is constructed by adopting a K nearest neighbor algorithm, an edge set of a random walk graph is constructed based on the interrelation among labels in a training image label set, and the labels of an image to be labeled are automatically labeled by the random walk algorithm. The invention has good adaptability, accuracy and universality.

Description

Automatic image annotation method based on K nearest neighbor and random walk algorithm
Technical Field
The invention belongs to the field of image retrieval, and aims at the problem that manually marked images cannot compete with massive image marking tasks on the Internet, and automatic marking of the images is realized by using a K neighbor and random walk algorithm.
Background
The invention realizes automatic labeling of massive images of the Internet and provides basic support for image retrieval. The traditional manual image labeling method has large workload, and the subjectivity and the inaccuracy are inevitably brought, so that the automatic image labeling of a computer is imperative. The automatic labeling of the image is to make a computer automatically add semantic keywords capable of reflecting the content of the image to the image, and the use of the automatic labeling can effectively improve the difficulty of the current image retrieval.
The K-nearest neighbor algorithm is a typical representative of the lazy learning method, has no obvious training process, and has the advantages of high classification precision, insensitivity to abnormal values and no data input assumption. The random walk algorithm was first described mathematically by einstein in 1926. Since many entities in nature move in unpredictable ways, random walk algorithms are used to describe such unstable movement processes in which a mobile node randomly selects a direction and speed to move from a current location to a new location. The random walk algorithm is a global optimization method and has the advantage of being not easy to fall into a local minimum value.
Disclosure of Invention
The invention aims to improve the accuracy of similarity calculation between images by comprehensively considering the difference between discrete features and continuous features of the images and based on Hamming loss and a Gaussian kernel function, reduce the time complexity and the space complexity of the algorithm by constructing a probability graph model based on a K nearest neighbor algorithm, and realize automatic annotation of the images by performing random walk on the probability graph model. The method has good adaptability, accuracy and universality.
The image automatic labeling method based on the K nearest neighbor and the random walk algorithm comprises the following steps:
step (a 1): extracting the features of the image to form a training set
Figure BDA0002187899940000017
And test set
Figure BDA0002187899940000018
Where i is the number of the image,
Figure BDA0002187899940000011
for the ith image xiIs determined by the feature vector of (a),
Figure BDA0002187899940000012
for continuous features, D1Is the number of consecutive features that are,
Figure BDA0002187899940000013
Figure BDA0002187899940000014
for discrete features, D is the total number of features,
Figure BDA0002187899940000015
is xiLabel set y ofiThe tag vector of (a) is determined,
Figure BDA0002187899940000016
as a total label set,/qThe number of the Q label in the L is Q, the Q is the number of the label, and the Q is the total number of the labels;
step (a 2): computing x based on Hamming losses and Gaussian functionsiAnd xjSimilarity (x) betweeni,xj) (i, j ═ 1,2, … m + n); step (a 3): probability graph model constructed based on K nearest neighbors
Figure BDA0002187899940000021
Wherein
Figure BDA0002187899940000022
Is composed of
Figure BDA0002187899940000023
The set of the vertices of (a) is,
Figure BDA0002187899940000024
is composed of
Figure BDA0002187899940000025
The edge set of (1);
step (a 4): prediction probability vector of image belonging to each label based on random walk algorithm
Figure BDA0002187899940000026
Wherein
Figure BDA0002187899940000027
Is xiBelong toqThe prediction probability of (i ═ m +1, m +2, …, m + n, Q ═ 1,2, …, Q);
step (a 5): construction of a predicted tag set y 'of an image based on predicted probabilities'i(i＝m+1,m+2,…,m+n)。
The method for calculating the similarity between the images based on the Hamming loss and the Gaussian kernel function comprises the following steps:
step (B1) constructs x based on Hamming lossesiAnd xjSimilarity of each discrete feature therebetween
Figure BDA0002187899940000028
(i, j ═ 1,2, … m + n, and i and j cannot be greater than m at the same time);
step (B2) constructs x based on Gaussian kernel functioniAnd xjSimilarity of each successive feature therebetween
Figure BDA0002187899940000029
Wherein
Figure BDA00021878999400000210
Representing a vector
Figure BDA00021878999400000211
And
Figure BDA00021878999400000212
the distance between the two adjacent electrodes is less than the total distance,
Figure BDA00021878999400000213
is a regulatory factor;
step (B3) is performed by applying NomSimiliity (x)i,xj) And NumSimiliity (x)i,xj) Weighted summation, construction of xiAnd xjSimilarity between them
Figure BDA00021878999400000214
The method for constructing the probability map model based on the K nearest neighbor comprises the following steps:
step (C1): structure xiIn the training set
Figure BDA00021878999400000221
Middle K nearest neighbor
Figure BDA00021878999400000215
Wherein K is
Figure BDA00021878999400000216
The number of the middle elements, x represents χtrainAll images in (1) and xiAfter the similarity between the images is sorted from big to small, x is one of the first K most similar images;
step (C2): structure of the device
Figure BDA00021878999400000217
Set of vertices of
Figure BDA00021878999400000218
Wherein
Figure BDA00021878999400000219
r is
Figure BDA00021878999400000220
The number of the middle vertex;
step (C3): structure of the device
Figure BDA0002187899940000031
Edge set of
Figure BDA0002187899940000032
Wherein
Figure BDA0002187899940000033
Wherein s is
Figure BDA0002187899940000034
The number of the middle vertex is,
Figure BDA0002187899940000035
are each vrAnd vsA set of labels corresponding to the image;
step (C4): constructing a probabilistic graphical model
Figure BDA0002187899940000036
The steps of constructing the prediction probability of each label of the image based on the random walk algorithm are as follows:
step (D1): the structure is based on
Figure BDA0002187899940000037
Transition matrix of
Figure BDA0002187899940000038
Figure BDA0002187899940000039
Wherein
Figure BDA00021878999400000310
Is composed of
Figure BDA00021878999400000311
Row r +1 and column s +1,
Figure BDA00021878999400000312
step (D2): the structure is based on
Figure BDA00021878999400000313
Is a hop probability vector
Figure BDA00021878999400000314
Wherein 1 isK+1A K +1 dimensional column vector with each component being 1;
step (D3): the structure is based on
Figure BDA00021878999400000315
Formula of random walk
Figure BDA00021878999400000316
Wherein k is the iteration number, alpha is the probability of jumping during random walk,
Figure BDA00021878999400000317
is the probability distribution vector at the kth random walk time,
Figure BDA00021878999400000318
a probability distribution vector corresponding to 0 is k;
step (D4): continuously iterating until obtaining stable probability distribution vector
Figure BDA00021878999400000319
Wherein
Figure BDA00021878999400000320
Satisfy the requirement of
Figure BDA00021878999400000321
Is an iteration error;
step (D5): calculating a final probability distribution vector
Figure BDA00021878999400000322
Wherein
Figure BDA00021878999400000323
Is 1qIn that
Figure BDA00021878999400000327
A prior probability of (1);
a step (D6) of calculating a prediction probability vector of each label to which the image belongs
Figure BDA00021878999400000324
Wherein
Figure BDA00021878999400000325
Is xiBelong toqThe probability of prediction of (a) is,
Figure BDA00021878999400000326
the steps of constructing the image prediction label set based on the label prediction probability adopted by the invention are as follows:
step (E1) of calculating
Figure BDA0002187899940000045
InqAverage length of the label set of the image of
Figure BDA0002187899940000041
(q＝1,2,…,Q)；
Step (E2) of calculating
Figure BDA0002187899940000046
Middle image xiPredicted length of the tag set of
Figure BDA0002187899940000042
(i＝m+1,m+2,…,m+n)
Step (E3) of
Figure BDA0002187899940000043
Sorting from big to small;
step (E4) of
Figure BDA0002187899940000044
From big to smallSelecting front length (y'i) And (4) taking the set of labels corresponding to the individual probabilities as an image prediction label set to finish automatic labeling of the image.
The invention has the following advantages:
1. the invention can label all types of images and has strong universality.
2. The invention can process images containing continuous features and discrete features and has strong adaptability.
3. The method is used for automatically marking the image based on the K nearest neighbor and the random walk algorithm, and is high in robustness and accuracy.
Drawings
FIG. 1 is a flow chart of the present invention for computing inter-image similarity based on Hamming loss and Gaussian kernel function
FIG. 2 is a flow chart of the present invention for constructing a probabilistic graphical model based on K-nearest neighbors
FIG. 3 is a flow chart of the present invention for constructing the prediction probability of each label belonging to an image based on the random walk algorithm
FIG. 4 is a flow chart of constructing an image prediction tag set based on tag prediction probability according to the present invention
FIG. 5 is a simplified flow chart of the present invention
Detailed Description
The invention relates to a method for constructing image similarity measurement based on Hamming loss and Gaussian kernel function, which constructs a probability graph model based on a K nearest neighbor algorithm and realizes automatic annotation of images by random walk on the probability graph model.
The process of calculating the similarity between images based on Hamming loss and Gaussian kernel function is as follows:
(1) as shown in fig. 1, the similarity between images with respect to discrete features is calculated by hamming loss, and the similarity between images with respect to continuous features is calculated by gaussian kernel function;
(2) and carrying out weighted average on the similarity between the discrete features and the similarity between the continuous features to obtain the similarity between the images.
The process of constructing the probability map model based on the K neighbors is as follows:
(1) as shown in fig. 2, a vertex set of the probability map model is constructed based on K neighbors of the image, and an edge set of the probability map model is constructed based on the correlation between corresponding label sets of the image;
(2) and combining the vertex set and the edge set into a probability graph model.
The process of constructing the prediction probability of each label of the image based on the random walk algorithm is as follows:
(1) constructing a state transition matrix and a jump probability vector in a random walk process based on a probability map model diagram as shown in FIG. 3;
(2) obtaining probability vectors of the image on each vertex in the probability map model through random walk;
(3) the probability that the image belongs to each label is calculated based on the probability distribution vector.
The process of constructing the image prediction tag set based on the tag prediction probability is as follows:
(1) as shown in fig. 4, the average length of the tag sets of the images belonging to the respective tags and the length of the predicted tag set of the image are calculated;
(2) a set of predictive labels for the image is constructed.

Claims (1)

1. An automatic image labeling method based on K neighbors and random walks is characterized in that similarity between images is calculated based on Hamming loss and a Gaussian kernel function, a probability model graph is constructed based on the K neighbors, prediction probabilities of the images belonging to all labels are constructed based on the random walks, an image prediction label set is constructed based on the label prediction probabilities, and the method sequentially comprises the following steps:
step (a 1): extracting the features of the image to form a training set
Figure FDA0002719534990000011
And test set
Figure FDA0002719534990000012
Where i is the number of the image,
Figure FDA0002719534990000013
for the ith image xiIs determined by the feature vector of (a),
Figure FDA0002719534990000014
for continuous features, D1Is the number of consecutive features that are,
Figure FDA0002719534990000015
for discrete features, D is the total number of features,
Figure FDA0002719534990000016
is xiLabel set y ofiThe vector of the labels is then used to,
Figure FDA0002719534990000017
L＝{l1,l2,…,lQas the total label set, lqThe number of the Q label in the L is Q, the number of the label is Q, and the number of the total label is Q;
step (a 2): computing x based on Hamming losses and Gaussian functionsiAnd xjSimilarity (x) betweeni,xj)(i,j＝1,2,…m+n)；
Step (a 3): probability model graph constructed based on K nearest neighbors
Figure FDA0002719534990000018
Wherein
Figure FDA0002719534990000019
Is composed of
Figure FDA00027195349900000110
The set of the vertices of (a) is,
Figure FDA00027195349900000111
is composed of
Figure FDA00027195349900000112
The edge set of (1);
step (a 4): prediction summary for image belonging to each label based on random walk algorithmRate vector
Figure FDA00027195349900000113
Wherein
Figure FDA00027195349900000114
Is xiBelong toqThe prediction probability of (i ═ m +1, m +2, …, m + n, Q ═ 1,2, …, Q);
step (a 5): construction of a predicted tag set y 'of an image based on predicted probabilities'i(i＝m+1,m+2,…,m+n)；
The method for calculating the similarity between the images based on the Hamming loss and the Gaussian kernel function comprises the following steps:
step (B1) constructs x based on Hamming lossesiAnd xjSimilarity between features with respect to each other
Figure FDA00027195349900000115
And i and j cannot be greater than m simultaneously);
step (B2) constructs x based on Gaussian kernel functioniAnd xjSimilarity between successive features
Figure FDA0002719534990000021
Wherein
Figure FDA0002719534990000022
Representing a vector
Figure FDA0002719534990000023
And
Figure FDA0002719534990000024
the distance between the two adjacent electrodes is less than the total distance,
Figure FDA0002719534990000025
is a regulatory factor;
step (B3) is performed by applying NomSimiliity (x)i,xj) And NumSimiliity (x)i,xj) Weighted summation, construction of xiAnd xjSimilarity between them
Figure FDA0002719534990000026
The method for constructing the probability model graph based on the K neighbors comprises the following steps:
step (C1): structure xiIn the training set
Figure FDA0002719534990000027
Middle K nearest neighbor
Figure FDA0002719534990000028
Figure FDA0002719534990000029
Wherein K is
Figure FDA00027195349900000210
Number of elements (A) in (B), where x belongs to xiAt xtrainK in (1) is near neighbor represented in xtrainThe image corresponding to all the characteristic vectors in the image is xiIn the sequence of similarity from large to small, x is positioned in the first K;
step (C2): structure of the device
Figure FDA00027195349900000211
Set of vertices of
Figure FDA00027195349900000212
Wherein
Figure FDA00027195349900000213
r is
Figure FDA00027195349900000214
The number of the first vertex;
step (C3): structure of the device
Figure FDA00027195349900000215
Edge set of
Figure FDA00027195349900000216
Wherein
Figure FDA00027195349900000217
Wherein s is
Figure FDA00027195349900000218
The number of the second vertex in the list,
Figure FDA00027195349900000219
are each vr、vsA set of labels for the corresponding image;
step (C4): constructing a probabilistic model graph
Figure FDA00027195349900000220
The method for constructing the prediction probability of the image belonging to each label based on the random walk comprises the following steps:
step (D1): the structure is based on
Figure FDA0002719534990000031
Transition matrix of
Figure FDA0002719534990000032
Figure FDA0002719534990000033
Wherein
Figure FDA0002719534990000034
Is composed of
Figure FDA0002719534990000035
Row r +1 and column s +1,
Figure FDA0002719534990000036
step (D2): the structure is based on
Figure FDA0002719534990000037
Is a hop probability vector
Figure FDA0002719534990000038
Wherein 1 isK+1Is a K +1 dimensional column vector with a component of 1;
step (D3): the structure is based on
Figure FDA0002719534990000039
Formula of random walk
Figure FDA00027195349900000310
Where k is the probability of the occurrence of a jump when the iteration number alpha is random walk,
Figure FDA00027195349900000311
is the probability distribution vector at the kth random walk time,
Figure FDA00027195349900000312
a probability distribution vector corresponding to 0 is k;
step (D4): continuously iterating until obtaining stable probability distribution vector
Figure FDA00027195349900000313
Wherein
Figure FDA00027195349900000314
Satisfy the requirement of
Figure FDA00027195349900000315
Is an iteration error;
step (D5): calculating a final probability distribution vector
Figure FDA00027195349900000316
Wherein
Figure FDA00027195349900000317
Is 1qIn that
Figure FDA00027195349900000318
A prior probability of (1);
a step (D6) of calculating a prediction probability vector of each label to which the image belongs
Figure FDA00027195349900000319
Figure FDA00027195349900000320
Wherein
Figure FDA00027195349900000321
Is xiBelong toqThe probability of prediction of (a) is,
Figure FDA00027195349900000322
the image prediction label set is constructed based on the label prediction probability, and the steps are as follows:
step (E1) of calculating
Figure FDA00027195349900000323
InqAverage length of the label set of the image of
Figure FDA00027195349900000324
Step (E2) of calculating
Figure FDA0002719534990000041
Middle image xiPredicted length of the tag set of
Figure FDA0002719534990000042
Figure FDA0002719534990000043
Step (E3) of
Figure FDA0002719534990000044
Sorting according to the sequence from big to small;
step (E4) of
Figure FDA0002719534990000045
Selecting the front length (y) in the sequence from big to smalli') labels corresponding to the probabilities, and forming an image prediction label set by the collection of the labels.
CN201910822291.5A 2019-09-02 2019-09-02 Automatic image annotation method based on K nearest neighbor and random walk algorithm Active CN110516092B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910822291.5A CN110516092B (en) 2019-09-02 2019-09-02 Automatic image annotation method based on K nearest neighbor and random walk algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910822291.5A CN110516092B (en) 2019-09-02 2019-09-02 Automatic image annotation method based on K nearest neighbor and random walk algorithm

Publications (2)

Publication Number Publication Date
CN110516092A CN110516092A (en) 2019-11-29
CN110516092B true CN110516092B (en) 2020-12-01

Family

ID=68629210

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910822291.5A Active CN110516092B (en) 2019-09-02 2019-09-02 Automatic image annotation method based on K nearest neighbor and random walk algorithm

Country Status (1)

Country Link
CN (1) CN110516092B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116049476A (en) * 2023-03-06 2023-05-02 福建福清核电有限公司 Remote sensing image semantic locating method based on multi-level likelihood expansion

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105808752A (en) * 2016-03-10 2016-07-27 大连理工大学 CCA and 2PKNN based automatic image annotation method
CN109800818A (en) * 2019-01-25 2019-05-24 宝鸡文理学院 A kind of image meaning automatic marking and search method and system

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102298605B (en) * 2011-06-01 2013-04-17 清华大学 Image automatic annotation method and device based on digraph unequal probability random search
CN108268510B (en) * 2016-12-30 2022-01-28 华为技术有限公司 Image annotation method and device
US11899669B2 (en) * 2017-03-20 2024-02-13 Carnegie Mellon University Searching of data structures in pre-processing data for a machine learning classifier
CN109670552B (en) * 2018-12-24 2023-03-10 苏州大学 Image classification method, device and equipment and readable storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105808752A (en) * 2016-03-10 2016-07-27 大连理工大学 CCA and 2PKNN based automatic image annotation method
CN109800818A (en) * 2019-01-25 2019-05-24 宝鸡文理学院 A kind of image meaning automatic marking and search method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"基于K近邻的多标签学习方法研究";余强;《中国优秀硕士学位论文全文数据库 信息科技辑》;20140915(第09期);第I138-729页 *
"聚类分析及其在图像处理中的应用";肖宇;《中国博士学位论文全文数据库 信息科技辑》;20130515(第5期);第I138-53页 *

Also Published As

Publication number Publication date
CN110516092A (en) 2019-11-29

Similar Documents

Publication Publication Date Title
Gao et al. A semi-supervised convolutional neural network-based method for steel surface defect recognition
WO2022068196A1 (en) Cross-modal data processing method and device, storage medium, and electronic device
CN110309331B (en) Cross-modal deep hash retrieval method based on self-supervision
CN110472090B (en) Image retrieval method based on semantic tags, related device and storage medium
CN111080400B (en) Commodity recommendation method and system based on gate control graph convolution network and storage medium
Yaseen et al. Deep learning hyper-parameter optimization for video analytics in clouds
WO2018150812A1 (en) Balancing active learning
Adhikari et al. Iterative bounding box annotation for object detection
CN110009430B (en) Cheating user detection method, electronic device and computer readable storage medium
Islam et al. InceptB: a CNN based classification approach for recognizing traditional bengali games
CN114186084A (en) Online multi-mode Hash retrieval method, system, storage medium and equipment
CN110929119A (en) Data annotation method, device, equipment and computer storage medium
CN110516092B (en) Automatic image annotation method based on K nearest neighbor and random walk algorithm
CN113610610B (en) Session recommendation method and system based on graph neural network and comment similarity
ElAlami Unsupervised image retrieval framework based on rule base system
Zhang et al. NAS4FBP: Facial beauty prediction based on neural architecture search
CN115424012A (en) Lightweight image semantic segmentation method based on context information
Janković Babić A comparison of methods for image classification of cultural heritage using transfer learning for feature extraction
Bahrami et al. Automatic image annotation using an evolutionary algorithm (IAGA)
Shavit et al. From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search
CN113987170A (en) Multi-label text classification method based on convolutional neural network
CN112101086A (en) Face clustering method based on link prediction
Aggarwal et al. Object Detection Based Approaches in Image Classification: A Brief Overview
CN113743168B (en) Urban flyer identification method based on micro-depth neural network search
CN116977021B (en) Automatic pushing method for system butt joint based on big data

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