CN116342906A - Cross-domain small sample image recognition method and system - Google Patents
Cross-domain small sample image recognition method and system Download PDFInfo
- Publication number
- CN116342906A CN116342906A CN202310258589.4A CN202310258589A CN116342906A CN 116342906 A CN116342906 A CN 116342906A CN 202310258589 A CN202310258589 A CN 202310258589A CN 116342906 A CN116342906 A CN 116342906A
- Authority
- CN
- China
- Prior art keywords
- sample
- samples
- network
- small sample
- target domain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 43
- 238000009826 distribution Methods 0.000 claims abstract description 37
- 238000006243 chemical reaction Methods 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims abstract description 13
- 230000000630 rising effect Effects 0.000 claims abstract 3
- 238000000605 extraction Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010428 oil painting Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
Description
技术领域technical field
本发明属于计算机视觉及图像处理领域,更具体地,涉及一种跨域小样本图像识别方法及系统。The invention belongs to the field of computer vision and image processing, and more specifically relates to a cross-domain small-sample image recognition method and system.
背景技术Background technique
目前,基于深度学习的方法在许多计算机视觉任务上都取得了优异的表现。然而这些性能强大的深度学习模型,往往都依赖于大规模的数据集和长时间的训练过程,需要投入较多的人力资源、时间成本和昂贵的计算代价。在这种情况下,小样本图像识别问题成为目前深度学习领域中关键的研究方向之一。相比于传统的大量样本驱动的图像识别,小样本图像识别可以在样本量有限的情况下,对新类别样本实现准确的预测分类,更符合真实的应场景。然而,在更实际的应用中,从同一个域内采集样本来完成大量的小样本分类任务是很困难的,当训练和测试数据分布不一致时,即源域数据与目标域数据的分布不同,二者间存在域偏移,模型更难以泛化,为了区别于传统小样本学习的问题设置,这种场景下的小样本学习问题被定义为“跨域小样本学习”。Currently, deep learning-based methods have achieved excellent performance on many computer vision tasks. However, these powerful deep learning models often rely on large-scale data sets and long-term training processes, requiring more human resources, time costs, and expensive computing costs. In this case, the problem of small-sample image recognition has become one of the key research directions in the field of deep learning. Compared with the traditional image recognition driven by a large number of samples, small sample image recognition can achieve accurate prediction and classification of new categories of samples under the condition of limited sample size, which is more in line with real application scenarios. However, in more practical applications, it is difficult to collect samples from the same domain to complete a large number of small sample classification tasks. When the distribution of training and testing data is inconsistent, that is, the distribution of source domain data is different from that of target domain data. There is a domain shift between them, and the model is more difficult to generalize. In order to distinguish it from the problem setting of traditional small-sample learning, the small-sample learning problem in this scenario is defined as "cross-domain small-sample learning".
先用的方法是基于模型微调的。这类方法基于元学习“learning to learn”的思想,旨在使模型在训练时学习与任务无关的知识,以便模型不对训练数据过拟合,能够更快地泛化到新任务上。例如,文章“Model-Agnostic Meta-Learning for Fast Adaptationof Deep Networks,Proceedings of the International Conference on MachineLearning(ICML),2017.”中提出元学习的思想有效解决跨域小样本分类的问题。The previous method is based on model fine-tuning. This type of method is based on the idea of meta-learning "learning to learn", which aims to enable the model to learn task-independent knowledge during training, so that the model does not overfit the training data and can generalize to new tasks faster. For example, the article "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks, Proceedings of the International Conference on Machine Learning (ICML), 2017." proposes the idea of meta-learning to effectively solve the problem of cross-domain small sample classification.
现有基于微调的跨域小样本识别有明显的局限性,对于每次输入新任务,模型都要进行微调的操作是非常复杂的,特别是对于规模较大的模型,参数微调会消耗大量计算成本和时间,因此,上述技术并不是一个本质的解决方案。The existing fine-tuning-based cross-domain small-sample recognition has obvious limitations. For each input of a new task, the operation of fine-tuning the model is very complicated, especially for large-scale models, parameter fine-tuning will consume a lot of calculations cost and time, therefore, the above technique is not an essential solution.
发明内容Contents of the invention
针对现有技术的缺陷,本发明的目的在于提供一种跨域小样本图像识别方法及系统,旨在解决现有基于微调的跨域小样本识别技术对于每次输入的新任务都要进行一次参数微调操作的复杂性;以及现有的小样本识别方法无法解决域间隙,泛化性能差的问题。Aiming at the defects of the prior art, the purpose of the present invention is to provide a cross-domain small-sample image recognition method and system, aiming at solving the problem that the existing cross-domain small-sample recognition technology based on fine-tuning needs to be performed once for each new input task. The complexity of parameter fine-tuning operations; and the existing small sample recognition methods cannot solve the problem of domain gap and poor generalization performance.
为实现上述目的,第一方面,本发明提供了一种跨域小样本图像识别方法,包括以下步骤:In order to achieve the above object, in the first aspect, the present invention provides a cross-domain small-sample image recognition method, comprising the following steps:
确定训练好的小样本识别网络;所述小样本识别网络用于对不同类别的样本进行匹配分类;所述小样本识别网络的训练过程需要用到图像生成网络,所述图像生成网络包括:变分自编码器模块和风格转换模块,所述变分自编码器模块用于提取并重建目标域样本的特征分布,所述变分自编码器包括中间参数,用于梯度上升将目标域样本重建成风格更复杂的样本;所述风格转换模块用于对源域样本进行风格化以得到属于目标域数据分布的带标签训练样本;其中,不同的图像风格对应不同的样本类别或数据域;Determine the trained small-sample recognition network; the small-sample recognition network is used to match and classify samples of different categories; the training process of the small-sample recognition network needs to use an image generation network, and the image generation network includes: variable Divided into a self-encoder module and a style conversion module, the variational self-encoder module is used to extract and reconstruct the feature distribution of the target domain samples, and the variational self-encoder includes intermediate parameters for gradient ascent to reconstruct the target domain samples into a sample with a more complex style; the style conversion module is used to stylize the source domain sample to obtain a labeled training sample belonging to the target domain data distribution; wherein, different image styles correspond to different sample categories or data domains;
将待识别的目标域样本输入到训练好的小样本识别网络,以进行预测分类,得到图像识别结果。Input the target domain samples to be recognized to the trained small-sample recognition network for predictive classification and image recognition results.
在一个可能的实施方式中,所述小样本识别网络包括:特征提取模块和度量匹配模块;In a possible implementation manner, the small sample recognition network includes: a feature extraction module and a metric matching module;
所述特征提取模块用于提取输入样本的特征;The feature extraction module is used to extract the features of the input samples;
所述度量匹配模块用于对不同类别样本进行匹配分类。The metric matching module is used for matching and classifying samples of different categories.
在一个可能的实施方式中,所述小样本识别网络的训练过程如下:In a possible implementation manner, the training process of the small sample recognition network is as follows:
对小样本识别网络F进行训练时,对于输入的每个任务T,从M类图像中循环随机选取N类图像,为每类图像确定K个样本作为支持集S,为每类图像确定q个样本作为查询集Q,T=(S,Q),输入图像生成网络G之后得到生成样本将生成样本/>输入小样本识别网络中进行预测识别计算得到损失LT,更新小样本识别网络F的参数同时,更新上述图像生成网络G的中间参数以生成更复杂的目标域风格样本,继续循环对小样本识别网络进行训练,直至训练好的小样本识别网络满足需求。When training the small-sample recognition network F, for each input task T, randomly select N types of images from M types of images in a loop, determine K samples for each type of image as the support set S, and determine q samples for each type of image The sample is used as a query set Q, T=(S, Q), and the generated sample is obtained after inputting the image generation network G will generate a sample /> Input the small-sample recognition network to perform predictive recognition calculations to obtain the loss L T , update the parameters of the small-sample recognition network F, and at the same time update the intermediate parameters of the above-mentioned image generation network G to generate more complex target domain style samples, and continue to cycle through small-sample recognition The network is trained until the trained small sample recognition network meets the requirements.
在一个可能的实施方式中,所述风格转换模块将所述变分自编码器输出的风格化参数作为风格特征进行风格化,以保留原有样本的内容特征且生成具有目标域数据分布特征的新样本。In a possible implementation manner, the style transformation module uses the stylization parameters output by the variational autoencoder as style features to stylize, so as to retain the content characteristics of the original samples and generate the new samples.
在一个可能的实施方式中,所述度量匹配模块用于对当前任务示例的查询集和支持集进行匹配分类,具体包括:对N类支持集样本计算类别中心,对查询集的每个样本计算到N个类别中心的距离,将查询集每个样本分类到距离最近的类别中心,以完成对查询集样本的识别分类。In a possible implementation manner, the metric matching module is used to match and classify the query set and support set of the current task example, specifically including: calculating the category center for N types of support set samples, and calculating the category center for each sample of the query set The distance to the N category centers, classify each sample in the query set to the nearest category center to complete the identification and classification of the query set samples.
在一个可能的实施方式中,所述小样本识别网络的整体目标函数为:In a possible implementation manner, the overall objective function of the small sample recognition network is:
其中,Lω表示对风格化查询集计算的分类损失,α表示小样本识别网络的参数,A表示基于风格化支持集/>和对应小样本识别网络参数α所选择的分类器,ω为小样本识别网络的输出结果。Among them, L ω represents the stylized query set The calculated classification loss, α represents the parameters of the small sample recognition network, and A represents the stylized support set/> And the classifier selected by the corresponding small sample recognition network parameter α, ω is the output result of the small sample recognition network.
第二方面,本发明提供了一种跨域小样本图像识别系统,包括:In the second aspect, the present invention provides a cross-domain small-sample image recognition system, including:
识别网络确定单元,用于确定训练好的小样本识别网络;所述小样本识别网络用于对不同类别的样本进行匹配分类;所述小样本识别网络的训练过程需要用到图像生成网络,所述图像生成网络包括:变分自编码器模块和风格转换模块,所述变分自编码器模块用于提取并重建目标域样本的特征分布,所述变分自编码器包括中间参数,用于梯度上升将目标域样本重建成风格更复杂的样本;所述风格转换模块用于对源域样本进行风格化以得到属于目标域数据分布的带标签训练样本;其中,不同的图像风格对应不同的样本类别或数据域;The recognition network determination unit is used to determine the trained small-sample recognition network; the small-sample recognition network is used to match and classify samples of different categories; the training process of the small-sample recognition network needs to use an image generation network, so The image generation network includes: a variational self-encoder module and a style conversion module, the variational self-encoder module is used to extract and reconstruct the feature distribution of the target domain samples, and the variational self-encoder includes intermediate parameters for Gradient ascent reconstructs the target domain samples into samples with more complex styles; the style conversion module is used to stylize the source domain samples to obtain labeled training samples belonging to the target domain data distribution; where different image styles correspond to different sample class or data field;
样本识别单元,用于将待识别的目标域样本输入到训练好的小样本识别网络,以进行预测分类,得到图像识别结果。The sample recognition unit is used to input the target domain samples to be recognized to the trained small-sample recognition network to perform prediction classification and obtain image recognition results.
在一个可能的实施方式中,所述小样本识别网络包括:特征提取模块和度量匹配模块;所述特征提取模块用于提取输入样本的特征;所述度量匹配模块用于对不同类别样本进行匹配分类,具体为:对当前任务示例的查询集和支持集进行匹配分类,具体包括:对N类支持集样本计算类别中心,对查询集的每个样本计算到N个类别中心的距离,将查询集每个样本分类到距离最近的类别中心,以完成对查询集样本的识别分类。In a possible implementation manner, the small sample recognition network includes: a feature extraction module and a metric matching module; the feature extraction module is used to extract features of input samples; the metric matching module is used to match different types of samples Classification, specifically: matching and classifying the query set and support set of the current task example, specifically including: calculating the category center for N-type support set samples, calculating the distance from each sample in the query set to N category centers, and querying Collect each sample and classify it to the nearest category center to complete the identification and classification of the query set samples.
在一个可能的实施方式中,该系统还包括:识别网络训练单元,用于对小样本识别网络F进行训练时,对于输入的每个任务T,从M类图像中循环随机选取N类图像,为每类图像确定K个样本作为支持集S,为每类图像确定q个样本作为查询集Q,T=(S,Q),输入图像生成网络G之后得到生成样本将生成样本/>输入小样本识别网络中进行预测识别计算得到损失LT,更新小样本识别网络F的参数同时,更新上述图像生成网络G的中间参数以生成更复杂的目标域风格样本,继续循环对小样本识别网络进行训练,直至训练好的小样本识别网络满足需求。In a possible implementation manner, the system also includes: a recognition network training unit, for training the small-sample recognition network F, for each input task T, cyclically randomly selects N types of images from M types of images, Determine K samples for each type of image as the support set S, determine q samples for each type of image as the query set Q, T=(S, Q), and generate samples after inputting the image generation network G will generate a sample /> Input the small-sample recognition network to perform predictive recognition calculations to obtain the loss L T , update the parameters of the small-sample recognition network F, and at the same time update the intermediate parameters of the above-mentioned image generation network G to generate more complex target domain style samples, and continue to cycle through small-sample recognition The network is trained until the trained small sample recognition network meets the requirements.
在一个可能的实施方式中,所述图像生成网络中风格转换模块将所述变分自编码器输出的风格化参数作为风格特征进行风格化,以保留原有样本的内容特征且生成具有目标域数据分布特征的新样本。In a possible implementation, the style conversion module in the image generation network uses the stylization parameters output by the variational autoencoder as style features for stylization, so as to retain the content characteristics of the original samples and generate A new sample of the distribution characteristics of the data.
第三方面,本申请提供一种电子设备,包括:至少一个存储器,用于存储程序;至少一个处理器,用于执行存储器存储的程序,当存储器存储的程序被执行时,处理器用于执行第一方面或第一方面的任一种可能的实现方式所描述的方法。In a third aspect, the present application provides an electronic device, including: at least one memory for storing programs; at least one processor for executing the programs stored in the memory, and when the programs stored in the memory are executed, the processor is used for executing the first The method described in one aspect or any possible implementation of the first aspect.
第四方面,本申请提供一种计算机可读存储介质,计算机可读存储介质存储有计算机程序,当计算机程序在处理器上运行时,使得处理器执行第一方面或第一方面的任一种可能的实现方式所描述的方法。In a fourth aspect, the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program runs on a processor, the processor executes any one of the first aspect or the first aspect. A possible implementation of the described method.
第五方面,本申请提供一种计算机程序产品,当计算机程序产品在处理器上运行时,使得处理器执行第一方面或第一方面的任一种可能的实现方式所描述的方法。In a fifth aspect, the present application provides a computer program product, which, when the computer program product runs on a processor, causes the processor to execute the method described in the first aspect or any possible implementation manner of the first aspect.
总体而言,通过本发明所构思的以上技术方案与现有技术相比,具有以下有益效果:Generally speaking, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects:
本发明提供一种跨域小样本图像识别方法及系统,在训练小样本识别网络模型时,输入待测图像,采用特征提取网络实现对于输入支持集和查询集样本的特征提取。由于在训练阶段,特征提取网络充分学习了有关目标域的分布信息,因此即使测试样本和训练样本之间存在域间隙,在特征提取阶段网络也能够有效提取到样本中类别相关的特征,有助于区分不同类别样本。The present invention provides a cross-domain small-sample image recognition method and system. When training a small-sample recognition network model, an image to be tested is input, and a feature extraction network is used to realize feature extraction for input support set and query set samples. Since the feature extraction network has fully learned the distribution information about the target domain during the training phase, even if there is a domain gap between the test sample and the training sample, the network can effectively extract the category-related features in the sample during the feature extraction phase, which is helpful. to distinguish different types of samples.
本发明提供一种跨域小样本图像识别方法及系统,选择匹配度量模块来训练小样本识别模型,通过训练灵活的度量方式,匹配不同类别样本之间特征的相似度,可以有效的找到样本之间的对应关系,进而有效的匹配识别。The present invention provides a cross-domain small-sample image recognition method and system. The matching measurement module is selected to train the small-sample recognition model. By training a flexible measurement method and matching the similarity of features between different types of samples, the difference between the samples can be effectively found. The corresponding relationship between them, and then effectively match and identify.
本发明提供一种跨域小样本图像识别方法及系统,提供的基于对抗的生成网络模型,包括变分自编码器模块和风格转换模块,能够在训练阶段有效引入目标域信息,提高模型对目标域的泛化能力,使得小样本识别模型在目标域上达到更准确的识别效果。The present invention provides a method and system for cross-domain small-sample image recognition. The generated network model based on confrontation includes a variational autoencoder module and a style conversion module, which can effectively introduce target domain information in the training phase and improve the accuracy of the model. The generalization ability of the domain enables the small-sample recognition model to achieve more accurate recognition on the target domain.
附图说明Description of drawings
图1是本发明实施例提供的跨域小样本图像识别方法流程图;FIG. 1 is a flowchart of a cross-domain small-sample image recognition method provided by an embodiment of the present invention;
图2是本发明实施例提供的跨域小样本识别的架构示意图;Fig. 2 is a schematic diagram of the architecture of cross-domain small sample recognition provided by the embodiment of the present invention;
图3是本发明实施例提供的风格化生成示意图;Fig. 3 is a schematic diagram of stylized generation provided by an embodiment of the present invention;
图4是本发明实施例提供的跨域小样本图像识别系统架构图。Fig. 4 is an architecture diagram of a cross-domain small-sample image recognition system provided by an embodiment of the present invention.
具体实施方式Detailed ways
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本发明,并不用于限定本发明。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
本文中术语“和/或”,是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。本文中符号“/”表示关联对象是或者的关系,例如A/B表示A或者B。The term "and/or" in this article is an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and B exists alone These three situations. The symbol "/" in this document indicates that the associated object is an or relationship, for example, A/B indicates A or B.
本文中的说明书和权利要求书中的术语“第一”和“第二”等是用于区别不同的对象,而不是用于描述对象的特定顺序。例如,第一响应消息和第二响应消息等是用于区别不同的响应消息,而不是用于描述响应消息的特定顺序。The terms "first" and "second" and the like in the specification and claims herein are used to distinguish different objects, rather than to describe a specific order of objects. For example, the first response message and the second response message are used to distinguish different response messages, rather than describing a specific order of the response messages.
在本申请实施例中,“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请实施例中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其它实施例或设计方案更优选或更具优势。确切而言,使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。In the embodiments of the present application, words such as "exemplary" or "for example" are used as examples, illustrations or illustrations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application shall not be interpreted as being more preferred or more advantageous than other embodiments or design schemes. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete manner.
在本申请实施例的描述中,除非另有说明,“多个”的含义是指两个或者两个以上,例如,多个处理单元是指两个或者两个以上的处理单元等;多个元件是指两个或者两个以上的元件等。In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more, for example, multiple processing units refer to two or more processing units, etc.; multiple A component refers to two or more components or the like.
首先,对本申请实施例中涉及的技术术语进行介绍。First, technical terms involved in the embodiments of the present application are introduced.
(1)风格化(1) Stylization
图像风格化又可以称为风格迁移,即将一张具有艺术特色的图像的风格迁移到一张普通的图像上,使原有的图像保留原始内容的同时,具有独特的艺术风格,如卡通、漫画、油画、水彩、水墨等。Image stylization can also be called style migration, which means transferring the style of an image with artistic characteristics to an ordinary image, so that the original image retains the original content while having a unique artistic style, such as cartoons, comics, etc. , oil painting, watercolor, ink and so on.
(2)域(2) domain
不同域指的样本数据分布不同,例如图像不同的艺术风格具有不同的数据分布,即不同艺术风格的图像属于不同的域。Different domains refer to different sample data distributions. For example, images with different artistic styles have different data distributions, that is, images with different artistic styles belong to different domains.
接下来,对本申请实施例中提供的技术方案进行介绍。Next, the technical solutions provided in the embodiments of the present application are introduced.
图1是本发明实施例提供的跨域小样本图像识别方法流程图;如图1所示,包括以下步骤:Fig. 1 is a flowchart of a cross-domain small-sample image recognition method provided by an embodiment of the present invention; as shown in Fig. 1 , it includes the following steps:
S101,确定训练好的小样本识别网络;所述小样本识别网络用于对不同类别的样本进行匹配分类;所述小样本识别网络的训练过程需要用到图像生成网络,所述图像生成网络包括:变分自编码器模块和风格转换模块,所述变分自编码器模块用于提取并重建目标域样本的特征分布,所述变分自编码器包括中间参数,用于梯度上升将目标域样本重建成风格更复杂的样本;所述风格转换模块用于对源域样本进行风格化以得到属于目标域数据分布的带标签训练样本;其中,不同的图像风格对应不同的样本类别或数据域;S101, determine the trained small-sample recognition network; the small-sample recognition network is used to match and classify samples of different categories; the training process of the small-sample recognition network needs to use an image generation network, and the image generation network includes : Variational autoencoder module and style conversion module, the variational autoencoder module is used to extract and reconstruct the feature distribution of the target domain samples, the variational autoencoder includes intermediate parameters, used for gradient ascent to convert the target domain The sample is reconstructed into a sample with a more complex style; the style conversion module is used to stylize the source domain sample to obtain a labeled training sample belonging to the target domain data distribution; wherein, different image styles correspond to different sample categories or data domains ;
S102,将待识别的目标域样本输入到训练好的小样本识别网络,以进行预测分类,得到图像识别结果。S102. Input the target domain samples to be recognized to the trained small-sample recognition network to perform prediction classification and obtain image recognition results.
具体地,首先确定预训练好的图像生成网络G和小样本识别网络F;所述图像生成网络G包含:变分自编码器模块和风格转换模块;所述变分自编码器模块用于提取并重建目标域样本的特征分布,其中间参数ε用于梯度上升产生更难的风格参数,所述风格转换模块用于对源域样本进行风格化以得到属于目标域数据分布的带标签训练样本;所述小样本识别网络F包含:特征提取模块和度量匹配模块;所述特征提取模块用于提取输入样本的特征,所述度量匹配模块用于对不同类别样本进行匹配分类。Specifically, first determine the pre-trained image generation network G and small sample recognition network F; the image generation network G includes: a variational autoencoder module and a style conversion module; the variational autoencoder module is used to extract And reconstruct the feature distribution of the target domain samples, the intermediate parameter ε is used for gradient ascent to generate more difficult style parameters, and the style conversion module is used to stylize the source domain samples to obtain labeled training samples belonging to the target domain data distribution ; The small sample recognition network F includes: a feature extraction module and a metric matching module; the feature extraction module is used to extract the characteristics of the input samples, and the metric matching module is used to match and classify different types of samples.
如图2所示,本发明提供的跨域小样本识别方法及系统的架构包括两个部分:As shown in Figure 2, the framework of the cross-domain small sample identification method and system provided by the present invention includes two parts:
(1)图像生成预训练网络包括变分自编码器模块/>和风格转换模块{F,g};所述变分自编码器模块用于提取并重建目标域样本的特征分布,其中间参数ε用于梯度上升产生更难的风格参数,所述风格转换模块用于对源域样本进行风格化以得到属于目标域数据分布的带标签训练样本。(1) Image generation pre-training network Includes Variational Autoencoder module /> and the style conversion module {F, g}; the variational autoencoder module is used to extract and reconstruct the feature distribution of the target domain samples, and the intermediate parameter ε is used for gradient ascent to generate more difficult style parameters, the style conversion module It is used to stylize the source domain samples to obtain labeled training samples belonging to the target domain data distribution.
(2)小样本识别网络T:包括特征提取模块和度量匹配模块;所述特征提取模块用于提取输入样本的特征,所述度量匹配模块用于对不同类别样本进行匹配分类。(2) Small-sample recognition network T: includes a feature extraction module and a metric matching module; the feature extraction module is used to extract features of input samples, and the metric matching module is used to match and classify different types of samples.
在一个具体的实施例中,本发明提供了一种跨域小样本识别方法,包括如下步骤:In a specific embodiment, the present invention provides a cross-domain small sample identification method, comprising the following steps:
在另一个示例中,本发明提供了一种跨域小样本识别系统,包括:In another example, the present invention provides a cross-domain small sample recognition system, including:
图像生成预训练模块G:包括变分自编码器单元和风格转换单元;所述变分自编码器单元用于提取并重建目标域样本的特征分布,其中间参数ε用于梯度上升产生更难的风格参数,所述风格转换单元用于对源域样本进行风格化以得到属于目标域数据分布的带标签训练样本。Image generation pre-training module G: includes a variational self-encoder unit and a style conversion unit; the variational self-encoder unit is used to extract and reconstruct the feature distribution of the target domain samples, and the intermediate parameter ε is used for gradient ascent to generate more difficult The style parameters of the style conversion unit are used to stylize the source domain samples to obtain labeled training samples belonging to the target domain data distribution.
小样本识别模块T:包括特征提取单元和度量匹配单元;所述特征提取单元用于提取输入样本的特征,所述度量匹配单元用于对不同类别样本进行匹配分类。Small sample identification module T: includes a feature extraction unit and a metric matching unit; the feature extraction unit is used to extract features of input samples, and the metric matching unit is used to match and classify different types of samples.
对所述小样本识别模块F进行训练时,对于输入的每个任务T,从M类图像中循环随机选取N类图像,为每类图像确定K个样本作为支持集S,为每类图像确定q个样本作为查询集Q,即T=(S,Q),其中 输入模块G之后得到生成样本/>将生成样本输入所述小样本识别模块中进行预测识别计算得到损失LT,更新识别模块F的参数同时,更新上述生成模块G的中间参数以生成更难的目标域风格,继而完成上述小样本识别模块F的训练。When training the small-sample recognition module F, for each task T input, randomly select N types of images from M types of images in a loop, determine K samples for each type of image as a support set S, and determine for each type of image q samples are used as the query set Q, that is, T=(S,Q), where After entering the module G to get the generated sample /> Input the generated samples into the small-sample recognition module for prediction and recognition calculation to obtain the loss L T , update the parameters of the recognition module F, and at the same time update the intermediate parameters of the above-mentioned generation module G to generate a more difficult target domain style, and then complete the above-mentioned small sample The training of recognition module F.
将待识别的目标域新类别样本输入到训练好的小样本识别模块中,以对待识别样本进行预测分类,输出对应的识别结果。Input the new category samples of the target domain to be recognized into the trained small sample recognition module to predict and classify the samples to be recognized, and output the corresponding recognition results.
在一个可选的示例中,所述变分自编码器单元用于对一组无标签未知域样本计算数据分布,并通过从其分布中采样锚点ε重建对应的风格化参数,参数具体包括均值和方差。In an optional example, the variational autoencoder unit is used to calculate the data distribution for a set of unlabeled unknown domain samples, and reconstruct the corresponding stylized parameters by sampling the anchor point ε from the distribution, and the parameters specifically include mean and variance.
在一个可选的示例中,所述风格转换单元用于对示例进行风格化,选择当前示例作为内容特征,上述变分自编码器输出的风格化参数作为风格特征进行风格化,输出的样本保留原有内容特征,因此其标签保留,同时具有目标域的数据分布特征。In an optional example, the style conversion unit is used to stylize the example, select the current example as the content feature, the stylization parameters output by the above variational autoencoder are used as the style feature for stylization, and the output samples are retained The original content characteristics, so its labels are preserved, and at the same time it has the data distribution characteristics of the target domain.
在一个可选的示例中,所述特征提取单元用于特征提取,具体包括对当前示例风格化后得到的样本进行特征提取。In an optional example, the feature extraction unit is used for feature extraction, specifically including performing feature extraction on samples obtained after stylization of the current example.
在一个可选的示例中,所述度量匹配单元用于对当前任务示例的查询集和支持集进行匹配分类,具体包括:对N类支持集样本计算类别中心,对查询集的每个样本计算到N个类别中心的距离,以完成对查询集样本的识别分类。In an optional example, the metric matching unit is used to match and classify the query set and support set of the current task example, specifically including: calculating the category center for N types of support set samples, and calculating the category center for each sample of the query set The distance to the centers of N categories to complete the identification and classification of query set samples.
在一个可选的示例中,所述识别模块的整体目标函数为:In an optional example, the overall objective function of the recognition module is:
其中,LT表示对风格化查询集计算的分类损失,α表示上述小样本识别模块的参数,A表示基于风格化支持集/>和对应小样本识别模块参数α所选择的分类器,ω即为其对应的输出结果。Among them, L T represents the stylized query set The calculated classification loss, α represents the parameters of the above small sample recognition module, and A represents the support set based on stylization /> And the classifier selected by the corresponding small sample recognition module parameter α, ω is its corresponding output result.
图3是本发明实施例提供的风格化生成示意图,如图3所示首先,我们先根据少量的目标域样本XT,算得其在特征空间的均值和方差/>以减弱由采样的偶然性带来的对网络训练的影响,其中/>之后再计算高斯分布的统计量N(ψ,ξ),其中/>对于每个小样本任务T={ST,QT},我们首先从高斯分布采样一个向量ε1,输入Dvae解码得到向量/>作为后面AdaIN网络的风格特征输入;将支持集图像ST和查询集图像QT输入EVGG,并将获得的特征作为AdaIN的另一个输入,AdaIN输出一些新的风格图像,表示为/>这些风格图像近似服从目标域分布。根据前几节的介绍,“ε1”即为“风格锚点”,因为VAE网络可以重建给定的M个目标域图像的分布。生成的风格化图像进一步输入任务模型,以解决小样本分类问题。在本发明中,选择RelationNet作为任务模型,其他解决小样本问题的模型也同样适用。为了搜索到更多符合目标域分布的风格,我们采用基于对抗的方法生成更困难的风格化样本,并尝试从“风格锚点”开始出发,迭代挖掘更多不可见的目标域分布。如图3所示,我们在任务模型的查询集上计算分类损失LT1,我们获取对ε1的反馈/>并为下一次迭代准备更困难的样本/>然后通过最小化LT更新任务模型参数,希望可以更准确地目标域图像进行分类,即使模型具有出色的泛化能力。Fig. 3 is a schematic diagram of stylized generation provided by the embodiment of the present invention. As shown in Fig. 3, first, we calculate the mean value in the feature space based on a small number of target domain samples X T and variance /> In order to weaken the impact on network training brought by the contingency of sampling, where /> Then calculate the statistics N(ψ,ξ) of the Gaussian distribution, where /> For each small-sample task T={S T ,Q T }, we first sample a vector ε 1 from the Gaussian distribution, and input D vae to decode the vector /> As the style feature input of the subsequent AdaIN network; the support set image ST and the query set image QT are input into EVGG , and the obtained features are used as another input of AdaIN, and AdaIN outputs some new style images, expressed as /> These style images approximately obey the target domain distribution. According to the introduction in the previous sections, “ε 1 ” is the “style anchor”, because the VAE network can reconstruct the distribution of given M target domain images. The generated stylized images are further fed into the task model to solve the few-shot classification problem. In the present invention, RelationNet is selected as the task model, and other models for solving small sample problems are also applicable. In order to search for more styles that fit the target domain distribution, we use an adversarial approach to generate more difficult stylized samples, and try to iteratively mine more invisible target domain distributions starting from the "style anchor". As shown in Figure 3, we compute the classification loss L T1 on the query set of the task model, and we obtain feedback on ε 1 /> and prepare more difficult samples for the next iteration /> Then update the task model parameters by minimizing LT , hoping to classify the target domain image more accurately, even if the model has excellent generalization ability.
图4是本发明实施例提供的跨域小样本图像识别系统架构图,如图4所示,包括:Fig. 4 is a cross-domain small-sample image recognition system architecture diagram provided by an embodiment of the present invention, as shown in Fig. 4, including:
识别网络训练单元410,用于对小样本识别网络F进行训练时,对于输入的每个任务T,从M类图像中循环随机选取N类图像,为每类图像确定K个样本作为支持集S,为每类图像确定q个样本作为查询集Q,T=(S,Q),输入图像生成网络G之后得到生成样本将生成样本/>输入小样本识别网络中进行预测识别计算得到损失LT,更新小样本识别网络F的参数同时,更新上述图像生成网络G的中间参数以生成更复杂的目标域风格样本,继续循环对小样本识别网络进行训练,直至训练好的小样本识别网络满足需求。The recognition
识别网络确定单元420,用于确定训练好的小样本识别网络;所述小样本识别网络用于对不同类别的样本进行匹配分类;所述小样本识别网络的训练过程需要用到图像生成网络,所述图像生成网络包括:变分自编码器模块和风格转换模块,所述变分自编码器模块用于提取并重建目标域样本的特征分布,所述变分自编码器包括中间参数,用于梯度上升将目标域样本重建成风格更复杂的样本;所述风格转换模块用于对源域样本进行风格化以得到属于目标域数据分布的带标签训练样本;其中,不同的图像风格对应不同的样本类别或数据域;The recognition
样本识别单元430,用于将待识别的目标域样本输入到训练好的小样本识别网络,以进行预测分类,得到图像识别结果。The
应当理解的是,上述装置用于执行上述实施例中的方法,装置中相应的程序模块,其实现原理和技术效果与上述方法中的描述类似,该装置的工作过程可参考上述方法中的对应过程,此处不再赘述。It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment, and the corresponding program modules in the device have similar implementation principles and technical effects to the description in the above-mentioned method, and the working process of the device can refer to the corresponding program module in the above-mentioned method The process will not be repeated here.
基于上述实施例中的方法,本申请实施例提供了一种电子设备。该设备可以包括:至少一个用于存储程序的存储器和至少一个用于执行存储器存储的程序的处理器。其中,当存储器存储的程序被执行时,处理器用于执行上述实施例中所描述的方法。Based on the methods in the foregoing embodiments, the embodiments of the present application provide an electronic device. The apparatus may comprise at least one memory for storing a program and at least one processor for executing the program stored in the memory. Wherein, when the program stored in the memory is executed, the processor is configured to execute the methods described in the above embodiments.
基于上述实施例中的方法,本申请实施例提供了一种计算机可读存储介质,计算机可读存储介质存储有计算机程序,当计算机程序在处理器上运行时,使得处理器执行上述实施例中的方法。Based on the methods in the above-mentioned embodiments, the embodiments of the present application provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program runs on the processor, the processor executes the above-mentioned embodiment. Methods.
基于上述实施例中的方法,本申请实施例提供了一种计算机程序产品,当计算机程序产品在处理器上运行时,使得处理器执行上述实施例中的方法。Based on the methods in the foregoing embodiments, the embodiments of the present application provide a computer program product that, when the computer program product runs on a processor, causes the processor to execute the methods in the foregoing embodiments.
可以理解的是,本申请的实施例中的处理器可以是中央处理单元(centralprocessing unit,CPU),还可以是其他通用处理器、数字信号处理器(digitalsignalprocessor,DSP)、专用集成电路(application specific integrated circuit,ASIC)、现场可编程门阵列(field programmable gate array,FPGA)或者其他可编程逻辑器件、晶体管逻辑器件,硬件部件或者其任意组合。通用处理器可以是微处理器,也可以是任何常规的处理器。It can be understood that the processor in the embodiment of the present application may be a central processing unit (central processing unit, CPU), and may also be other general processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. A general-purpose processor can be a microprocessor, or any conventional processor.
本申请的实施例中的方法步骤可以通过硬件的方式来实现,也可以由处理器执行软件指令的方式来实现。软件指令可以由相应的软件模块组成,软件模块可以被存放于随机存取存储器(random access memory,RAM)、闪存、只读存储器(read-only memory,ROM)、可编程只读存储器(programmable rom,PROM)、可擦除可编程只读存储器(erasable PROM,EPROM)、电可擦除可编程只读存储器(electrically EPROM,EEPROM)、寄存器、硬盘、移动硬盘、CD-ROM或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器,从而使处理器能够从该存储介质读取信息,且可向该存储介质写入信息。当然,存储介质也可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。The method steps in the embodiments of the present application may be implemented by means of hardware, or may be implemented by means of a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (random access memory, RAM), flash memory, read-only memory (read-only memory, ROM), programmable read-only memory (programmable rom) , PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically erasable programmable read-only memory (electrically EPROM, EEPROM), register, hard disk, mobile hard disk, CD-ROM or known in the art any other form of storage medium. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be a component of the processor. The processor and storage medium can be located in the ASIC.
在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时,全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中,或者通过所述计算机可读存储介质进行传输。所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质(例如固态硬盘(solid state disk,SSD))等。In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in or transmitted via a computer-readable storage medium. The computer instructions may be transmitted from one website site, computer, server, or data center to another website site by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) , computer, server or data center for transmission. The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (solid state disk, SSD)) and the like.
可以理解的是,在本申请的实施例中涉及的各种数字编号仅为描述方便进行的区分,并不用来限制本申请的实施例的范围。It can be understood that the various numbers involved in the embodiments of the present application are only for convenience of description, and are not used to limit the scope of the embodiments of the present application.
本领域的技术人员容易理解,以上所述仅为本发明的较佳实施例而已,并不用以限制本发明,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,均应包含在本发明的保护范围之内。It is easy for those skilled in the art to understand that the above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention, All should be included within the protection scope of the present invention.
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310258589.4A CN116342906A (en) | 2023-03-14 | 2023-03-14 | Cross-domain small sample image recognition method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310258589.4A CN116342906A (en) | 2023-03-14 | 2023-03-14 | Cross-domain small sample image recognition method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116342906A true CN116342906A (en) | 2023-06-27 |
Family
ID=86885139
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310258589.4A Pending CN116342906A (en) | 2023-03-14 | 2023-03-14 | Cross-domain small sample image recognition method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116342906A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117132804A (en) * | 2023-07-04 | 2023-11-28 | 中国矿业大学 | Hyperspectral image classification method based on causal cross-domain small sample learning |
-
2023
- 2023-03-14 CN CN202310258589.4A patent/CN116342906A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117132804A (en) * | 2023-07-04 | 2023-11-28 | 中国矿业大学 | Hyperspectral image classification method based on causal cross-domain small sample learning |
CN117132804B (en) * | 2023-07-04 | 2024-04-05 | 中国矿业大学 | A hyperspectral image classification method based on causal cross-domain small sample learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kang et al. | Structured graph learning for clustering and semi-supervised classification | |
CN110069709B (en) | Intention recognition method, device, computer readable medium and electronic equipment | |
WO2021089012A1 (en) | Node classification method and apparatus for graph network model, and terminal device | |
CN113139051B (en) | Text classification model training method, text classification method, device and medium | |
CN112232395B (en) | Semi-supervised image classification method for generating countermeasure network based on joint training | |
CN109787958A (en) | Network flow real-time detection method and detection terminal, computer readable storage medium | |
CN111612022A (en) | Method, apparatus and computer storage medium for analyzing data | |
CN116579345B (en) | Named entity recognition model training method, named entity recognition method and named entity recognition device | |
CN114330588A (en) | A kind of picture classification method, picture classification model training method and related device | |
CN110189362B (en) | Efficient target tracking method based on multi-branch self-coding countermeasure network | |
CN116681961A (en) | Weak supervision target detection method based on semi-supervision method and noise processing | |
CN113434683A (en) | Text classification method, device, medium and electronic equipment | |
CN116151331B (en) | Training method of commodity marketing text generation model and commodity marketing text generation method | |
CN106326904A (en) | Device and method of acquiring feature ranking model and feature ranking method | |
CN116342906A (en) | Cross-domain small sample image recognition method and system | |
CN113140012A (en) | Image processing method, image processing apparatus, image processing medium, and electronic device | |
CN117992835B (en) | Multi-strategy label disambiguation partial multi-label classification method, device and storage medium | |
CN114881149A (en) | A model training method and device, and a target detection method and device | |
CN113761845B (en) | Text generation method, device, storage medium and electronic device | |
CN111626315A (en) | Model training method, object recognition method, device, medium, and electronic apparatus | |
WO2024091325A1 (en) | Purified contrastive learning for lightweight neural network training | |
CN108898227A (en) | Learning rate calculation method and device, disaggregated model calculation method and device | |
CN113010687B (en) | Exercise label prediction method and device, storage medium and computer equipment | |
CN115496137A (en) | Small sample classification method based on label propagation and distribution conversion and related device | |
CN114358011A (en) | Named entity extraction method and device and electronic equipment |
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 |