WO2016033708A1 - Systèmes et procédés de classification de données d'image - Google Patents

Systèmes et procédés de classification de données d'image Download PDF

Info

Publication number
WO2016033708A1
WO2016033708A1 PCT/CN2014/000825 CN2014000825W WO2016033708A1 WO 2016033708 A1 WO2016033708 A1 WO 2016033708A1 CN 2014000825 W CN2014000825 W CN 2014000825W WO 2016033708 A1 WO2016033708 A1 WO 2016033708A1
Authority
WO
WIPO (PCT)
Prior art keywords
training data
target code
neural network
training
network system
Prior art date
Application number
PCT/CN2014/000825
Other languages
English (en)
Inventor
Xiaoou Tang
Shuo YANG
Ping Luo
Chen Change Loy
Original Assignee
Xiaoou Tang
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 Xiaoou Tang filed Critical Xiaoou Tang
Priority to PCT/CN2014/000825 priority Critical patent/WO2016033708A1/fr
Priority to CN201480081756.1A priority patent/CN106687993B/zh
Publication of WO2016033708A1 publication Critical patent/WO2016033708A1/fr

Links

Images

Classifications

    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00—Arrangements for detecting or preventing errors in the information received
    • H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
    • H04L1/0056—Systems characterized by the type of code used
    • H04L1/0057—Block codes

Definitions

  • the present application generally relates to a field of target identification, more particularly, to an apparatus and a method for image data classification.
  • an apparatus for data classification may comprising: a target code generator configured to retrieve a plurality of training data samples and to generate a target code for each of the retrieved training data samples, wherein the training data samples being grouped into different classes; a target prediction generator configured to receive a plurality of arbitrary data samples and to generate a target prediction for each of the received arbitrary data samples; and a predictor configured to predict a class for each of the received arbitrary data sample based on the generated target code and the generated target prediction.
  • the method may comprise: retrieving a plurality of training data samples, wherein the training data samples being grouped into different classes; generating a target code for each of the retrieved training data samples; for an unclassified data sample, generating a target prediction for the unclassified data sample; and predicting a class for the unclassified data sample based on the generated target code and the generated target prediction.
  • the present invention brings extra benefits to neural network training. On one hand, more discriminative hidden features can form in the neural network system. On the other hand, and the predictions generated by the neural network system has error correcting capability.
  • Fig. 1 is a schematic diagram illustrating an apparatus for image data classification according to an embodiment of the present application.
  • Fig. 2 is a schematic diagram illustrating a target code generator according to an embodiment of the present application.
  • Fig. 3 is a schematic diagram illustrating an apparatus with a training unit according to another embodiment of the present application.
  • Fig. 4. is a schematic diagram illustrating the training unit according to another embodiment of the present application.
  • Fig. 5. is a schematic diagram illustrating a predictor according to an embodiment of the present application.
  • Fig. 6. is a schematic diagram illustrating a training unit according to another embodiment of the present application.
  • Fig. 7. is a schematic diagram illustrating a predictor according to another embodiment of the present application.
  • Fig. 8 is a schematic flowchart illustrating a method for image data classification according to an embodiment of the present application.
  • Fig. 9 is a schematic flowchart illustrating a process for generating a target code according to an embodiment of the present application.
  • Fig. 10 is a schematic flowchart illustrating a process for training a neural network system according to an embodiment of the present application.
  • Fig. 11 is a schematic flowchart illustrating a process for predicting a class for an unclassified data sample according to an embodiment of the present application.
  • Fig. 12 is a schematic flowchart illustrating a process for training a neural network system according to another embodiment of the present application.
  • Fig. 13 is a schematic flowchart illustrating a process for predicting a class for an unclassified data sample according to another embodiment of the present application.
  • FIG. 1 is a schematic diagram illustrating an exemplary apparatus 1000 for data classification with some disclosed embodiments.
  • the apparatus 1000 may be implemented using certain hardware, software, or a combination thereof.
  • the embodiments of the present application may be adapted to a computer program product embodied on one or more computer readable storage media (comprising but not limited to disk storage, CD-ROM, optical memory and the like) containing computer program codes.
  • the apparatus 1000 can be run in one or more system that may include a general purpose computer, a computer cluster, a mainstream computer, a computing device dedicated for providing online contents, or a computer network comprising a group of computers operating in a centralized or distributed fashion.
  • the apparatus 1000 may comprise a target code generator 100, a neural network system 200 and a predictor 300.
  • the target code generator 100 may configured to retrieve a plurality of training data samples and to generate a target code for each of the retrieved training data samples, wherein the training data samples being grouped into different classes.
  • the target prediction generator 200 may be configured to receive a plurality of arbitrary data samples and to generate a target prediction for each of the received arbitrary data samples.
  • the target prediction generator 200 may comprises a neural network system.
  • the neural network system may comprise at least one of a deep belief network and a convolutional network.
  • the neural network may consist of the convolutional filters, pooling layers, and locally or fully connected layers, which are well known in the art, and thus the detailed configurations thereof are omitted herein.
  • the predictor 300 may be configured to predict a class for each of the received arbitrary data sample based on the generated target code and the generated target prediction.
  • T be a set of integers, called the alphabet set.
  • An element in T is called a symbol.
  • T ⁇ 0, 1 ⁇ is a binary alphabet set.
  • a target code S is a matrix S ⁇ T n ⁇ l , wherein each row of a target code is called a codeword, l denotes the number of symbols in each codeword and n denotes the total number of codewords.
  • the target code can be constructed with a deterministic method, which is built on the Hadamard matrix.
  • For a target code S we denote be the set of empirical distributions of symbols in the rows of S, i. e.
  • ⁇ i is a vector of length
  • the Hamming distance between row i and row i' of a target code S.
  • Table 1 shows an example of a 1-of-K target code, which is typically used in deep learning for representing K classes.
  • Each of the K symbols either ‘0’ or ‘1’ , indicates the probability of a specific class.
  • the target coding can play additional roles, such as error correcting or facilitating better feature representation.
  • additional roles a target code S fulfilling specific requirements should be constructed.
  • the target code generator 100 further comprises a matrix generating module 110, a removing module 120, a changing module 130, and a selecting module 140.
  • the definition of Hadamard matrix requires that any pair of distinct rows and columns are orthogonal, respectively.
  • the removing module 120 is configured to let S BC ⁇ T (m- 1 ) ⁇ (m-1) obtained by removing the first row and the first column of H.
  • the changing module 130 is configured to remove a first row and a first column of the Hadamard matrix.
  • the above formulation yields the balanced target code S BC of size (m-1) ⁇ (m-1) , row sum m/2, column sum m/2, and pairwise Hamming distance is constant m/2.
  • the selecting module 140 is configured to randomly select a plurality of rows of the changed Hadamard matrix as the target code, wherein the number of rows is identical to that of the classes of the training data samples.
  • the target code may be represented as a vector.
  • the selecting module 140 is configured to randomly select c rows as balanced target codes for c classes, wherein each of the selected rows corresponds to one target code.
  • the class labels C BC ⁇ T K ⁇ (m-1) is constructed by choosing K codewords randomly from S BC ⁇ T (m-1) ⁇ (m-1) .
  • the apparatus 1000’ comprises a target code generator 100, a neural network system 200, a predictor 300, and a training unit 400.
  • the functions of the target code generator 100, the neural network system 200, and the predictor 300 have been described with reference to Fig. 1, and thus will be omitted hereinafter.
  • the training unit 400 is configured to train the neural network system with the retrieved training data samples such that the trained neural network system is capable of applying the convolutional filters, pooling layers, and locally or fully connected layers to the retrieved training data samples to generate said target predictions.
  • the target prediction may be represented as a vector.
  • the training unit 400 further comprises a drawing module 410, an error computing module 420, and a back-propagating module 430.
  • the drawing module 410 is configured to draw a training data sample from the training data samples, wherein each of the training data samples is associated with a corresponding ground-truth target code, for example, based on a class label of the training data sample.
  • the target code may be a ground-truth target code.
  • the error computing module 420 is configured to compute an error such as a Hamming distance between the generated target prediction of the training data sample and the ground-truth target code.
  • the back-propagating module 430 is configured to back-propagate the computed error through the neural network system so as to adjust weights on connections between neurons of the neural network system. In order to get a convergence result, the drawing module, the error computing module and the back-propagating module repeat processes of drawing, computing and back-propagating until the error is less than a predetermined value.
  • the predictor 300 further comprises a distance computing module 310, and an assigning module 320.
  • the distance computing module 310 is configured to compute Hamming distances between a target prediction of an unclassified data sample and the corresponding ground-truth target code of each class of the training samples. Since both the target prediction and the ground-truth target code are vectors having similar length, the distance between the target prediction and the ground-truth target code can be determined by calculating the Hamming distance. For example, if target prediction is ‘1110111’ , and ground-truth target code is ‘1010101’ , the Hamming distance is determined by calculating the number of positions at which the corresponding values are different. In this example, the Hamming distance is 2.
  • the assigning module 320 is configured to assign the unclassified data sample to a class corresponding to the minimum Hamming distance among the computed Hamming distances. That is to say, if the unclassified data sample is closest to a particular class (based on Hamming distance between its target prediction and ground-truth target code) , then the unclassified data sample is considered to be in the same class as the ground-truth code.
  • the training unit 400’ comprises a drawing module 410, an error computing module 420, a back-propagating module 430, and an extracting module 440.
  • the drawing module 410 may be configured to draw a training data sample from the training data samples, wherein each of the training data samples is associated with a corresponding ground-truth target code, for example, based on a class label of the training data sample.
  • the error computing module 420 may be configured to compute an error such as a Hamming distance between the generated target prediction of the training data sample and the ground-truth target code.
  • the back-propagating module 430 may be configured to back-propagate the computed error through the neural network system so as to adjust weights on connections between neurons of the neural network system.
  • the drawing module 410, the error computing module 420 and the back-propagating module 430 repeat processes of drawing, computing and back-propagating until the error is less than a predetermined value.
  • the extracting module 440 may be configured to extract hidden layer features from the penultimate layer of the neural network system and train a multiclass classifier based on the extracted hidden layer features and class labels of the training data samples, after the error is less than a predetermined value.
  • the hidden layer features will be used as training input of the multiclass classifier
  • the class labels will be used as training target of the multiclass classifier
  • the training input and the training target are used to train the multiclass classifier by optimizing the classifier’ sobjective function.
  • Given an unclassified data sample its hidden layer features may be extracted by the trained neural network system, and then fed into the multiclass classifier. Then, the multiclass classifier may output a class prediction for the unclassified data sample.
  • the predictor 300’ comprises a receiving module 340, a retrieving module 350, and a prediction generating module 360.
  • the receiving module 340 may be configured to receive an unclassified data sample.
  • the retrieving module 350 may be configured to retrieve the trained multiclass classifier from the training unit.
  • the prediction generating module 360 may be configured to generate a class prediction for the unclassified data sample by the trained multiclass classifier.
  • Fig. 8 is a schematic flowchart illustrating a method 2000 for data classification.
  • the method 2000 may be described in detail with respect to Fig. 8.
  • a plurality of training data samples is retrieved and a target code for each of the retrieved training data samples is generated by a target code generator, wherein the training data samples being grouped into different classes.
  • a target prediction for the unclassified data sample is generated by a neural network system.
  • the neural network system may consist of multiple layers of convolutional filters, pooling layers, and locally or fully connected layers.
  • the neural network system may comprise at least one of a deep belief network and a convolutional network.
  • the method further comprises a step S240 of training the neural network system with the retrieved training data samples such that the trained neural network system is capable of applying the convolutional filters, pooling layers, and locally or fully connected layers to the retrieved training data samples to generate said target predictions.
  • the step S220 of generating a target code comprises following steps.
  • a Hadamard matrix whose entries are either “+1” or “-1” , is generated.
  • a first row and a first column of the Hadamard matrix is removed.
  • “+1” is changed to “0” and “-1” is mapped to “1” .
  • a number of rows of changed Hadamard matrix are randomly selected as the target codes, wherein the number of the selected rows is identical to that of the classes of the training data samples and each of the selected rows corresponds to one target code.
  • step S230 at which a class for an unclassified data sample is predicted by a predictor based on the generated target code and the generated target prediction.
  • the step S240 of training a neural network system comprises following steps.
  • a training data sample is drawn from a predetermined training set, wherein the training data sample is associated with a corresponding target code, particularly a ground-truth target code, for example, based on a class label of the training data sample.
  • an error such as a Hamming distance between the generated target prediction and the ground-truth target code is computed.
  • the computed error is back-propagated through the neural network system so as to adjust weights on connections between neurons of the neural network system.
  • step S440 the steps S410-S430 are repeated until the error is less than a predetermined value, i. e. , until the training process is converged.
  • the step S230 of predicting a class for an unclassified data sample comprises following steps.
  • step S510 an unclassified data sampled is received.
  • step S520 Hamming distances between a target prediction of the unclassified data sample and the corresponding ground-truth target code of each class of the training samples is computed.
  • the distance between the target prediction and the ground-truth target code can be computed by calculating the Hamming distance. For example, if target prediction is ‘1110111’ , and ground-truth target code is ‘1010101’ , the Hamming distance is computed by calculating the number of positions at which the corresponding values are different. In this example, the Hamming distance may be 2.
  • the unclassified data sample is assigned to a class corresponding to the minimum Hamming distance among the computed Hamming distances. That is to say, if the unclassified data sample is closest to a particular class (based on Hamming distance between its target prediction and ground-truth target code) , then the unclassified data sample is considered to be in the same class as the ground-truth code.
  • the step S240’ of training a neural network system further comprises following steps.
  • a training data sample is drawn from a predetermined training set, wherein the training data sample is associated with a corresponding target code, particularly a ground-truth target code, for example, based on a class label of the training data sample.
  • step S420 an error between the generated target prediction and the ground-truth target code is computed.
  • the computed error is back-propagated through the neural network system so as to adjust weights on connections between neurons of the neural network system.
  • step S440 if the error is less than a predetermined value, i. e. , the training process is converged, the steps S410-S430 are repeated, otherwise, the method proceed with step S450 of extracting hidden layer features from the penultimate layer of the neural network system and training a multiclass classifier based on the extracted hidden layer features and class labels of the training data samples.
  • the hidden layer features will be used as training input of the multiclass classifier
  • the class labels will be used as training target of the multiclass classifier
  • the training input and the training target are used to train the multiclass classifier by optimizing the classifier’ sobjective function.
  • Given an unclassified data sample its hidden layer features may be extracted by the trained neural network system, and then fed into the multiclass classifier. Then, the multiclass classifier may output a class prediction for the unclassified data sample.
  • the step S230’ of predicting the class for an unclassified data sample comprises following steps.
  • step S540 an unclassified data sample is received.
  • step S550 the multiclass classifier trained in step S450 is retrieved.
  • a class prediction is generating for the unclassified data sample by the trained multiclass classifier.
  • present application provides a neural network system, with a balanced target coding unit to represent the target code of different data classes.
  • target codes are employed in the learning of a neural network along with a predetermined set of training data.
  • Prior arts often adopt a 1-of-K coding scheme in neural network training.
  • the balanced coding unit brings extra benefits to neural network training.
  • more discriminative hidden features can form in the neural network system.
  • the predictions generated by the neural network system has error correcting capability.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Medical Informatics (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

L'invention concerne un appareil servant à la classification de données d'image. L'appareil peut comprendre : un générateur de code cible configuré pour récupérer une pluralité d'échantillons de données d'apprentissage et pour générer un code cible pour chacun des échantillons de données d'apprentissage récupérés. Les échantillons de données d'apprentissage sont regroupés en différentes classes, et le code cible généré possède une dimension identique au nombre des classes. L'appareil peut en outre comprendre : un générateur de prédiction cible configuré pour recevoir une pluralité d'échantillons de données arbitraires et pour générer une prédiction cible pour chacun des échantillons de données arbitraire reçus; et un prédicteur configuré pour prévoir une classe pour chacun des échantillons de données arbitraires reçus en se basant sur le code cible généré et la prédiction cible générée. L'invention concerne également un procédé de classification de données d'image.
PCT/CN2014/000825 2014-09-03 2014-09-03 Systèmes et procédés de classification de données d'image WO2016033708A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2014/000825 WO2016033708A1 (fr) 2014-09-03 2014-09-03 Systèmes et procédés de classification de données d'image
CN201480081756.1A CN106687993B (zh) 2014-09-03 2014-09-03 用于图像数据分类的设备和方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2014/000825 WO2016033708A1 (fr) 2014-09-03 2014-09-03 Systèmes et procédés de classification de données d'image

Publications (1)

Publication Number Publication Date
WO2016033708A1 true WO2016033708A1 (fr) 2016-03-10

Family

ID=55438961

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/000825 WO2016033708A1 (fr) 2014-09-03 2014-09-03 Systèmes et procédés de classification de données d'image

Country Status (2)

Country Link
CN (1) CN106687993B (fr)
WO (1) WO2016033708A1 (fr)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107909151A (zh) * 2017-07-02 2018-04-13 小蚁科技（香港）有限公司 用于在人工神经网络中实现注意力机制的方法和系统
CN109472274A (zh) * 2017-09-07 2019-03-15 富士通株式会社 深度学习分类模型的训练装置和方法
CN109753978A (zh) * 2017-11-01 2019-05-14 腾讯科技（深圳）有限公司 图像分类方法、装置以及计算机可读存储介质
CN109946669A (zh) * 2019-03-18 2019-06-28 西安电子科技大学 基于深度置信网络的变体飞机高分辨距离像恢复方法
CN112765034A (zh) * 2021-01-26 2021-05-07 四川航天系统工程研究所 基于神经网络的软件缺陷预测方法
CN115797710A (zh) * 2023-02-08 2023-03-14 成都理工大学 基于隐藏层特征差异的神经网络图像分类性能提升方法
CN116794975A (zh) * 2022-12-20 2023-09-22 维都利阀门有限公司 电动蝶阀的智能控制方法及其系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111767735B (zh) * 2019-03-26 2024-08-16 北京京东尚科信息技术有限公司 执行任务的方法、装置及计算机可读存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050031219A1 (en) * 2002-09-06 2005-02-10 The Regents Of The University Of California Encoding and decoding of digital data using cues derivable at a decoder
US7831531B1 (en) * 2006-06-22 2010-11-09 Google Inc. Approximate hashing functions for finding similar content
CN103246893A (zh) * 2013-03-20 2013-08-14 西交利物浦大学 基于拒识的随机子空间的ecoc编码分类方法
CN103426004A (zh) * 2013-07-04 2013-12-04 西安理工大学 基于纠错输出编码的车型识别方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050031219A1 (en) * 2002-09-06 2005-02-10 The Regents Of The University Of California Encoding and decoding of digital data using cues derivable at a decoder
US7831531B1 (en) * 2006-06-22 2010-11-09 Google Inc. Approximate hashing functions for finding similar content
CN103246893A (zh) * 2013-03-20 2013-08-14 西交利物浦大学 基于拒识的随机子空间的ecoc编码分类方法
CN103426004A (zh) * 2013-07-04 2013-12-04 西安理工大学 基于纠错输出编码的车型识别方法

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107909151A (zh) * 2017-07-02 2018-04-13 小蚁科技（香港）有限公司 用于在人工神经网络中实现注意力机制的方法和系统
CN107909151B (zh) * 2017-07-02 2020-06-02 小蚁科技（香港）有限公司 用于在人工神经网络中实现注意力机制的方法和系统
CN109472274B (zh) * 2017-09-07 2022-06-28 富士通株式会社 深度学习分类模型的训练装置和方法
CN109472274A (zh) * 2017-09-07 2019-03-15 富士通株式会社 深度学习分类模型的训练装置和方法
CN109753978A (zh) * 2017-11-01 2019-05-14 腾讯科技（深圳）有限公司 图像分类方法、装置以及计算机可读存储介质
CN109753978B (zh) * 2017-11-01 2023-02-17 腾讯科技（深圳）有限公司 图像分类方法、装置以及计算机可读存储介质
CN109946669A (zh) * 2019-03-18 2019-06-28 西安电子科技大学 基于深度置信网络的变体飞机高分辨距离像恢复方法
CN109946669B (zh) * 2019-03-18 2022-12-02 西安电子科技大学 基于深度置信网络的变体飞机高分辨距离像恢复方法
CN112765034A (zh) * 2021-01-26 2021-05-07 四川航天系统工程研究所 基于神经网络的软件缺陷预测方法
CN112765034B (zh) * 2021-01-26 2023-11-24 四川航天系统工程研究所 基于神经网络的软件缺陷预测方法
CN116794975A (zh) * 2022-12-20 2023-09-22 维都利阀门有限公司 电动蝶阀的智能控制方法及其系统
CN116794975B (zh) * 2022-12-20 2024-02-02 维都利阀门有限公司 电动蝶阀的智能控制方法及其系统
CN115797710A (zh) * 2023-02-08 2023-03-14 成都理工大学 基于隐藏层特征差异的神经网络图像分类性能提升方法
CN115797710B (zh) * 2023-02-08 2023-04-07 成都理工大学 基于隐藏层特征差异的神经网络图像分类性能提升方法

Also Published As

Publication number Publication date
CN106687993A (zh) 2017-05-17
CN106687993B (zh) 2018-07-27

Similar Documents

Publication Publication Date Title
WO2016033708A1 (fr) Systèmes et procédés de classification de données d'image
Cakir et al. Hashing with mutual information
CN106599900B (zh) 一种识别图像中的字符串的方法和装置
US20170372169A1 (en) Method and apparatus for recognizing image content
Stewart et al. End-to-end people detection in crowded scenes
CN105447498B (zh) 配置有神经网络的客户端设备、系统和服务器系统
RU2693916C1 (ru) Распознавание символов с использованием иерархической классификации
Charalampous et al. On-line deep learning method for action recognition
Xi et al. Deep prototypical networks with hybrid residual attention for hyperspectral image classification
CN104112018B (zh) 一种大规模图像检索方法
CN110019652B (zh) 一种基于深度学习的跨模态哈希检索方法
Bansal et al. mrmr-pso: A hybrid feature selection technique with a multiobjective approach for sign language recognition
Cohen et al. Dnn or k-nn: That is the generalize vs. memorize question
Liu et al. Deep ordinal regression based on data relationship for small datasets.
CN107004140A (zh) 文本识别方法和计算机程序产品
US20200074273A1 (en) Method for training deep neural network (dnn) using auxiliary regression targets
CN114730398A (zh) 数据标签验证
CN111898703A (zh) 多标签视频分类方法、模型训练方法、装置及介质
CN109522432B (zh) 一种融合自适应相似度和贝叶斯框架的图像检索方法
CN107247755A (zh) 一种基于上下文序列记忆网络的个性化图像字幕生成方法
EP3876236A1 (fr) Extraction des structures chimiques des images numérisées
Alam et al. A multi-view convolutional neural network approach for image data classification
CN110199300A (zh) 用于自动编码器的模糊输入
Chen et al. Class-aware convolution and attentive aggregation for image classification
Zhang et al. Code consistent hashing based on information-theoretic criterion

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: 14901041

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: 14901041

Country of ref document: EP

Kind code of ref document: A1