Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1746 results about "Supervised training" patented technology

A supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples. An optimal scenario will allow for the algorithm to correctly determine the class labels for unseen instances.

Equipment fault diagnosis and prediction method based on deep learning

The invention relates to the technical field of equipment fault diagnosis, and discloses an equipment fault diagnosis and prediction method based on deep learning, and the method comprises the following steps: S1, collecting multi-modal data in real time through a plurality of sensors installed on equipment; s2, preprocessing the collected data; s3, constructing a hybrid deep learning model; s4, dynamic weighted fusion is performed on the features of different modal data by using an attention mechanism, and comprehensive feature representation is generated; s5, using the marked fault data and normal data to supervise and train the model; s6, inputting equipment operation data acquired in real time into the trained model, and judging the state of the equipment; and S7, generating a potential fault early warning signal based on a prediction result of the model. A piezoelectric vibration sensor and a thermal infrared imager are arranged on a motor bearing through vibration, temperature and sound sensors, vibration waveforms, thermal imaging slices and time-frequency diagrams are synchronously captured, and composite state characteristics such as mechanical wear and temperature anomaly of equipment are comprehensively reflected.
Owner:SHENZHEN JITON INTELLIGENT TECH CO LTD

Wind power fault dynamic early warning method and system based on multi-source heterogeneous data fusion

The invention relates to the field of fault early warning, in particular to a wind power fault dynamic early warning method and system based on multi-source heterogeneous data fusion. According to the method, multi-source data such as SCADA operation data, CMS vibration monitoring data and meteorological environment data of a wind turbine generator are collected in real time, standardization processing is carried out, and a multi-dimensional feature vector is constructed. And generating a fusion data set by using an adaptive weighted fusion algorithm, constructing a fault prediction model based on a deep convolutional neural network, and outputting a health state assessment value and a fault risk level in real time after historical fault sample supervised training. And when the risk level exceeds a threshold value, generating an early warning signal containing a fault type and a positioning and repairing suggestion, dynamically adjusting a monitoring parameter weight, iteratively updating a model, and realizing adaptive optimization of an early warning strategy. The problem that an existing method depends on single data source and multi-source data fusion is solved, and accurate dynamic early warning is achieved.
Owner:HEBEI JIANTOU NEW ENERGY CO LTD

Large-scene three-dimensional reconstruction method based on three-dimensional Gaussian sputtering

The invention discloses a large-scene three-dimensional reconstruction method based on three-dimensional Gaussian sputtering, and relates to computer graphics. The method comprises the following steps: collecting a multi-view image set of a large scene; obtaining a scene sparse point cloud according to the multi-view image set; performing monocular depth estimation on the multi-view image by using a pre-trained depth prediction network to obtain monocular depth estimation priori; the method comprises the following steps of: performing global training on a scene by utilizing scene sparse point cloud and monocular depth estimation prior to obtain an initial three-dimensional Gaussian model, and performing space grid division on the initial three-dimensional Gaussian model to obtain a plurality of scene blocks with axis alignment bounding boxes; setting image view angle data of each scene block; performing deep supervised training on the Gaussian ellipsoids in the plurality of scene blocks by using a parallel GPU (Graphics Processing Unit); combining the trained scene blocks to obtain a final three-dimensional Gaussian model; in view of low geometric structure reconstruction precision caused by only depending on color information of a multi-view image in large-scene three-dimensional rendering, the method improves the reconstruction precision of large-scene rendering.
Owner:JSTI GRP CO LTD +2

Hydropower station equipment fault analysis method based on state data mining

The invention discloses a hydropower station equipment fault analysis method based on state data mining, and relates to the technical field of hydropower station equipment intelligent fault diagnosis, and the method comprises the steps: collecting key operation parameters through deploying multiple types of sensors, and constructing a unified state time series data set; carrying out supervised training by adopting an LSTM network, extracting a dynamic feature vector, and constructing an AI state analysis model; introducing a micro-fluctuation abnormal coefficient WBYX, and evaluating the operation stability of the equipment; a coupling disturbance collaboration coefficient OHRD is calculated, and a fault conduction relation among multiple devices is identified; and calculating a trend evolution coefficient QSYH based on the state vector included angle offset, and analyzing whether the equipment operation trend is abnormal or not. By setting a multi-level threshold value, generation of a hierarchical early warning mechanism and a response strategy is realized, and the operation safety and the fault prediction capability of hydropower station equipment are effectively improved. The method is suitable for hydropower station key equipment state monitoring and intelligent operation and maintenance management in a complex environment.
Owner:SICHUAN HUADIAN MULIHE HYDROPOWER DEV CO LTD

Automatic data annotation method of ISP image signal processing visual sensor

The invention relates to an automatic data labeling method of an ISP image signal processing visual sensor. The method comprises the following steps: carrying out noise reduction and signal enhancement on an original image data stream acquired by an ISP image signal processing visual sensor to obtain a standardized image sequence; performing time sequence feature extraction to obtain a time sequence feature tensor; performing spatial feature extraction to obtain spatial-temporal feature representation; inputting a double-fold teacher-student network for semi-supervised training to obtain an initial image annotation model; performing quality evaluation based on the prediction probability distribution and the time sequence consistency to obtain a labeling result with a quality score; and storing a high-quality sample in the labeling result with the quality score into a sample buffer pool, carrying out sample screening based on entropy and distance measurement, and carrying out parameter updating on the initial image labeling model through an incremental learning strategy to obtain a target image labeling model. According to the invention, the reliability evaluation of the labeling result is realized, and the accuracy of automatic labeling is ensured.
Owner:SHENZHEN KEAN DIGITAL CO LTD

Image self-supervised learning method and system fusing contrast learning and feature mask modeling

The invention discloses an image self-supervised learning method and system fusing contrast learning and feature mask modeling. An original image which is low in cost and does not need to be labeled is used as training data, a double-branch self-supervised learning network is constructed, one branch is a comparison learning branch based on a SimCLR framework, the other branch is a mask self-encoder branch based on a mask feature model, and the whole network comprises an image preprocessing module, an image feature extraction module and a shared weight encoder. And carrying out self-supervised training by combining the two branches with a loss function specially designed for the two branches, and finally obtaining a pre-training model capable of fully extracting image features. According to the method, the advantages of comparative learning and feature mask modeling are combined, information is effectively extracted from unlabeled image data, and image understanding is enhanced. The method has the main advantages that the robustness is high, the method is particularly suitable for limited data sets in the remote sensing and medical fields, the model precision is improved, and the data requirement and labeling cost are reduced.
Owner:HUAZHONG NORMAL UNIV

Power transformer partial discharge signal extraction and diagnosis method combined with deep learning

The invention discloses a deep learning-combined power transformer partial discharge signal extraction and diagnosis method. The method comprises the following steps of S1, setting a multi-channel synchronous acquisition system in a power transformer body area to acquire a multi-dimensional original partial discharge data set; s2, preprocessing the acquired multi-dimensional original partial discharge data set; s3, performing time alignment and amplitude matching on the processed signal, and dividing the processed signal into a sliding time window to construct a standard input tensor; s4, constructing an attention enhancement model fused by the convolutional neural network and the bidirectional gating circulation unit; s5, performing supervised training on the attention enhancement model by using the labeled sample; s6, inputting the real-time signal into the training model, and outputting a discharge type label; s7, risk grade evaluation is carried out in combination with statistical characteristics; and S8, generating a structured diagnosis report and uploading the structured diagnosis report to a monitoring platform. According to the invention, multi-source signals and a depth model are fused, and intelligent diagnosis and risk assessment of transformer partial discharge are realized.
Owner:GANSU DIANTONG POWER ENG DESIGN CONSULTING CO LTD

Generation and evaluation method for obtaining long text description from laparoscopic surgery image

The invention discloses a generation and evaluation method for acquiring long text description from a laparoscopic surgery image, which comprises the following steps of: constructing a cue word containing the laparoscopic surgery image, short text description, a target bounding box and surgery knowledge, and constructing long text description data by utilizing a large language model based on the cue word; constructing an image long text description generation model which comprises a pre-trained visual encoder, a visual feature query converter, a language decoder and an external operation concept vector database; performing supervised training on the image long text description generation model by using the long text description data; constructing a long text description evaluation method to evaluate the trained model; the method comprises the following steps: acquiring an input laparoscope image video stream through a laparoscope image system, and screening a key frame as a to-be-processed image; and inputting a to-be-processed image into the trained and evaluated model to obtain an image long text description result. According to the method, the ability of understanding operation details in the image can be enhanced, and more comprehensive operation image description can be generated.
Owner:ZHEJIANG UNIV

Voice generation method and device, equipment and medium

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of medical health, financial science and technology and the like, and discloses a voice generation method which comprises the following steps: constructing a multi-language voice synthesis model, obtaining plain text data and paired voice text data, and constructing an expansion vocabulary; updating a language perception embedding layer and model parameters, and converting an input text into a mark sequence; and the encoder extracts context semantic features, extracts pronunciation rule features, and the decoder fuses the features to generate an acoustic feature sequence, and converts the acoustic feature sequence into target voice data. According to the invention, the multi-language speech synthesis model is combined with the language perception embedding layer, so that the speech generation capability of a low-resource language is improved; the text conversion accuracy is improved by expanding the vocabulary, the target language learning ability is enhanced by unsupervised training, the low data environment adaptability is optimized by supervised training, and the speech naturalness and fluency are improved by feature fusion.
Owner:PING AN TECH (SHENZHEN) CO LTD

Domain-adaptive retrieval enhancement generation method and system

The invention discloses a domain-adaptive retrieval enhancement generation method and system, and the method comprises the steps: carrying out the document analysis and semantic partitioning of a document through a semantic understanding model and a document rule, and storing document fragments; on the basis of the large language model and a preset question library, generating a question and disassembling the question; performing correlation evaluation and sorting on the initial retrieval results in combination with a retrieval technology; candidate content most matched with the cue words is screened out through a large language model, and question-retrieval fragments are scored and marked; performing fusion on the initial retrieval result and the scoring and labeling result to construct positive and negative samples, and constructing a supervised data set; and based on a preset loss function, utilizing the supervised data set to carry out supervised training on the knowledge semantic search model, replacing the RAG mixed search module, and carrying out continuous iteration. By means of the technical scheme, new domain knowledge and operation feedback data can be flexibly applied, and domain self-adaptive retrieval enhancement generation is achieved.
Owner:SI-TECH INFORMATION TECH CO LTD

Self Supervised Training of Machine-Learned Image Processing Models for Histopathology

An example computer-implemented method for self-supervised training of an image processing model for histopathology images is provided. The example method includes obtaining a reference histopathology image; generating an augmented histopathology image, wherein generating the augmented histopathology image comprises performing, for an input image, at least one of the following augmentations: applying a blur to the input image and injecting noise artifacts into the blurred input image; or cropping a plurality of portions from the input image, wherein the plurality of portions are determined based on a minimum overlap criterion that has been updated over one or more iterations; and training the image processing model based on a similarity of latent representations generated by the image processing model respectively for the reference histopathology image and the augmented histopathology image.
Owner:GOOGLE LLC

Smart grid fault self-healing method and system based on generative artificial intelligence

The present invention discloses a method and system for smart grid fault self-healing based on generative artificial intelligence, which relates to the field of smart grid fault self-healing. The method includes: obtaining and preprocessing multi-source heterogeneous data; generating a pre-trained language model and performing domain adaptability fine-tuning, adding a task-specific output layer; performing feature fusion using a multimodal data fusion method, and using annotated historical fault data sets for supervised training to obtain fault diagnosis results. Fault self-healing is modeled as a Markov decision process, and a deep reinforcement learning algorithm is used to interactively learn the optimal decision-making strategy with a power grid simulation environment, and an optimal fault self-healing plan is generated and converted into specific operation instructions. The present invention integrates multi-source heterogeneous data, performs accurate positioning and description generation, improves the reliability and self-healing ability of the smart grid, and ensures rapid recovery of normal operation when a power grid fails.
Owner:STATE GRID LIAONING ECONOMIC TECHN INST

Mask Transform and contrast learning-based hyperspectral image classification method

The invention discloses a hyperspectral image classification method based on mask Transform and contrast learning, and the method comprises the steps: obtaining and preprocessing hyperspectral image data, obtaining a sample set, and obtaining a training set based on the sample set; constructing an initial hyperspectral image classification model and a model overall loss function; dividing the training set into a labeled data set and a label-free data set, pre-training the initial hyperspectral image classification model based on the label-free data set and a model overall loss function, simplifying and recombining, and performing supervised training on the simplified and recombined model based on the labeled data set and a cross entropy loss function, and performing hyperspectral image classification through the trained model. According to the method, multi-scale mask reconstruction and local contrast learning are combined, so that the attention of the model to the ground feature in the hyperspectral image is improved, the space and channel information of the feature map is enriched, the weight of the ground feature is enhanced, and the accuracy and robustness of spectral image classification are improved.
Owner:EAST CHINA JIAOTONG UNIVERSITY

Target detection method and apparatus, electronic device, and readable storage medium

The present application relates to the technical field of machine learning, and discloses a target detection method and apparatus, an electronic device, and a readable storage medium, aiming at solving the problem of inaccurate target detection result caused by inaccurate image feature depth estimation in conventional target detection technology. The method comprises: performing feature extraction on a target image to obtain an image feature; processing the image feature by using a preset depth prediction model to obtain depth distribution of the image feature, wherein the preset depth prediction model is obtained by performing supervised training on the basis of a preset depth distribution loss function, the preset depth distribution loss function comprises one or more of a foreground depth distribution consistency loss function, a foreground area depth distribution entropy reduction constraint and a confusion area depth distribution entropy increase constraint; converting the image feature into an image aerial view feature by using the depth distribution; and performing target detection on the image aerial view feature to obtain a target detection result.
Owner:INSPUR (BEIJING) ELECTRONICS INFORMATION IND CO LTD

Semi-supervised multi-temporal satellite image time-varying information extraction method

The invention discloses a semi-supervised multi-temporal satellite image time-varying information extraction method, and belongs to the technical field of remote sensing image processing. The semantic change detection performance of the model and the detection precision of complex shape change ground objects are improved. The method comprises the following steps: constructing a semantic change detection model, carrying out full-supervised training on the semantic change detection model by using a binary change detection supervised loss function and a semantic segmentation supervised loss function by using a small amount of labeled dual-temporal remote sensing images to obtain an initial model, and obtaining a semantic change detection prediction result of each pair of images; using a pseudo label optimization strategy to optimize the semantic change detection prediction result of each pair of images; combining the obtained pseudo label data with high confidence and a small amount of labeled dual-temporal remote sensing images into a new training set, using the new training set to perform semi-supervised training on the initial model in a semantic change detection model, and using a consistency regularization combination loss function to perform supervised training to obtain a new model; and until a preset number of iterations is reached.
Owner:HARBIN AEROSPACE STAR DATA SYST TECH CO LTD +1

Automated label generation using a machine-learned language model

An online system may provide an instruction prompt to a machine-learned language model. The instruction prompt may include an instruction to generate an evaluation label of a training sample of a classification model and a textual format related to how data is arranged. The evaluation label may be used in a supervised training of the classification model. The online system may provide a batch of evaluation request prompts to the machine-learned language model. Each evaluation request prompt includes data that is at least partially arranged in the textual format described in the instruction prompt. The online system may receive a plurality of responses from the machine-learned language model. Each response includes the evaluation label corresponding to each evaluation request prompt. The online system may store at least evaluation labels and the data in the evaluation request prompts as training samples for the supervised training of the classification model.
Owner:MAPLEBEAR INC

Method for improving intelligent classification precision of distillate oil

The invention discloses a method for improving the intelligent classification precision of distillate oil, and the method comprises the steps: employing a method based on a threshold value during spectrum cleaning, and adding S-G to smooth and sharpen spectral features during data preprocessing; during model supervised training, the high-dimensional feature center of distillate oil types is increased, and the identification capability of the model on inter-class differences is enhanced. The method can effectively improve the fraction oil spectrum classification precision, improve the model generalization ability, and provide a more accurate and efficient intelligent classification scheme for refinery enterprises.
Owner:NANJING RICHISLAND INFORMATION TECH CO LTD

Document image tampering detection model training method, tampering detection method and device

The invention provides a training method of a document image tampering detection model and a tampering detection method and device.The training method of the document image tampering detection model comprises the steps that multi-scale visual domain features are extracted from a sample document image, and multi-scale frequency domain compressed sensing features are extracted from frequency domain information; acquiring tampered area edge mask data from the document image; fusing the multi-scale visual domain features and the multi-scale frequency domain compressed sensing features to obtain multi-modal fusion features; performing semi-supervised training on the multi-scale sensing network by taking the multi-scale visual domain feature as a sample feature of a first prediction head, taking the multi-modal fusion feature as a sample feature of a second prediction head, taking a real label or a pseudo label as a sample label and taking joint loss as a loss function to obtain a document image tampering detection model; according to the method provided by the invention, document image tampering pixel-level detection under low labeling cost is realized, and the detection precision of a document image tampering detection model is improved.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI

User feedback for specific portions of responses generated using a large language model (LLM)

Implementations relate to providing a user feedback mechanism that enables a user to provide feedback towards one or more specific portions of a response. The response can be generated based on processing of a user query using a generative model such as a large language model (LLM). The one or more specific portions can be a textual portion that includes textual content, and / or a media content portion that include media content such as one or more images, one or more videos, one or more audio pieces, etc. The feedback towards one or more of the specific portions of the response can be utilized in training or fine-tuning the generative model (or an additional generative model) via approaches such as supervised training or reinforced learning.
Owner:GOOGLE LLC

Method of enhancing abnormal area of ground-penetrating radar image based on hybrid-supervised learning

A method of enhancing an abnormal area of a ground-penetrating radar image based on hybrid-supervised learning includes the steps of: building a database including a real image set, a simulation image set and a simulation image label set; adopting a generative adversarial network; processing semi-supervised training and unsupervised training alternately to obtain a trained model, then inputting a real radar image with abnormal area that needs to be enhanced into the model and processing through the generative network to output an abnormal-area-enhanced image. The method overcomes the problems of differences in characteristics between simulated images and real images, and low utilization efficiency of real image information by unsupervised methods, and improves the utilization efficiency of the enhanced network for real image information, the saliency of abnormal areas on real images, and the generalization ability of the enhanced network, therefore effectively enhances the significance of abnormal areas in ground-penetrating radar images.
Owner:CHENGDU UNIVERSITY OF TECHNOLOGY

Intelligent monitoring and fault diagnosis integrated RV reducer control system and method

The invention relates to the technical field of RV speed reducers, in particular to an intelligent monitoring and fault diagnosis integrated RV speed reducer control system and method. Collecting multi-mode operation data of the RV speed reducer, wherein the multi-mode operation data comprises vibration, temperature, sound and current data; feature extraction is carried out on the multi-modal operation data, an adaptive feature fusion method based on an attention mechanism is designed, weights of different features are dynamically adjusted, and comprehensive and intelligent state monitoring is achieved; constructing a fault diagnosis model based on a multi-branch convolutional neural network, and performing supervised training on the model by using historical operation data and fault labels to realize high-precision fault classification; a knowledge distillation technology is adopted to compress the trained model, the model is deployed into the RV reducer, and online real-time diagnosis is achieved; according to the method, the value of multi-source heterogeneous data is fully mined, and the intelligent level of RV reducer fault diagnosis is improved.
Owner:NANTONG INST OF TECH

Target detection domain adaptation method based on random context consistency reasoning

The invention discloses a target detection domain adaptation method based on random context consistency reasoning. A semi-supervised learning teacher-student model framework is adopted, slow updating is performed through index moving average of a teacher model, so that the model can obtain information from main knowledge learned by student models, and a self-supervised effect is achieved. A random complementary mask module is introduced to mask partial local visual features which the network seriously depends on, so that the network is encouraged to utilize other visual clues in the context. In addition, the phenomenon that most self-training frameworks seriously depend on pseudo tags is avoided through an internal context consistency reasoning module, and the self context reasoning ability of the student model is improved by constructing a self-supervised training normal form of the student model. And finally, constructing a self-training framework based on a teacher-student model through an external context consistency reasoning module, and encouraging a student model to make correct prediction on a masked area by utilizing a pseudo tag, with global priori knowledge, of the teacher model.
Owner:HANGZHOU DIANZI UNIV

Three-dimensional hand posture estimation and action recognition algorithm based on deep learning

The invention provides a three-dimensional hand posture estimation and action recognition algorithm based on deep learning, and the algorithm comprises the steps: obtaining a public first person hand action data set FPHA, carrying out the preprocessing, taking a video sample according to an experiment condition and a set proportion, and dividing the video sample into a training set and a test set; a three-dimensional hand posture estimation and action recognition model which is based on deep learning and comprises a double-layer transformer and a lightweight posture smoothing network smopnet is established; inputting the processed first person hand action data set training set into a posture estimation and action recognition model according to a set batch by utilizing a hierarchical moving window thought to carry out supervised training, and sending the preprocessed data into a pre-trained ResNet model to carry out shallow feature extraction; the method comprises the following steps: firstly, carrying out two-dimensional hand gesture recognition on the two-dimensional hand gesture, then sending the two-dimensional hand gesture to a first-layer transformer, carrying out gesture estimation and smooth optimization by utilizing coded short-time inter-frame time sequence information, fusing the two-dimensional hand gesture, operation object classification information and a feature map after the first-layer coded time sequence information by a second-layer transformer in a longer time span, and modeling a semantic relationship between the gesture and the action so as to judge the type of the action. Through the method provided by the invention, three-dimensional hand posture estimation with higher precision and action type judgment with higher accuracy can be carried out on the first person hand action video.
Owner:GUILIN UNIV OF ELECTRONIC TECH

Industrial product defect automatic classification method and system

The invention provides an industrial product defect automatic classification method and system, and the method comprises the steps: collecting original industrial product defect image data, and constructing a labeled image sample set and an unlabeled image sample set; constructing a training image sample set based on the labeled image sample set and the unlabeled image sample set in combination with a plurality of image synthesis strategies; based on the training image sample set, introducing a transfer learning strategy and fusing an attention mechanism, and constructing and optimizing an industrial product defect classification model; performing semi-supervised joint training and online learning based on the training image sample set and the real-time small-batch image sample set; and constructing an industrial product defect identification log based on the real-time image flow sample set, the classification model parameters and the corresponding classification prediction function. On the basis of multi-strategy image enhancement and semi-supervised training, transfer learning and a channel attention mechanism are fused, expansion of industrial product defect image samples and fine defect identification are achieved, and the method is suitable for an intelligent defect detection system in various industrial manufacturing fields.
Owner:SHANGHAI DINGPEI INFORMATION TECHNOLOGY CO LTD

Track application reasoning method and system based on track pre-training large model

The invention relates to the technical field of track analysis, in particular to a track application reasoning method and system based on a track pre-training large model, and the method comprises the steps: obtaining a high-precision open-source track data set, cleaning the data set, and constructing a self-supervised training data set; constructing a track pre-training large model for extracting high-dimensional semantic features of the track; based on the self-supervised training data set, constructing a learning loss function to pre-train the track pre-training large model; aiming at a specific track downstream application, constructing a small sample labeling training data set; and cross-domain application training and reasoning are realized based on a small sample labeling training data set. According to the method, the semantic features of the track are extracted by using the track pre-training large model, and cross-domain application training and reasoning are carried out based on cross-domain data, so that the requirement on the number of application labeling samples in special fields can be remarkably reduced.
Owner:Chinese People's Liberation Army Cyberspace Force Information Engineering University

Multi-view conversion method based on multi-view consistency diffusion model

The invention relates to the technical field of image conversion, and discloses a multi-view conversion method based on a multi-view consistency diffusion model, and the multi-view consistency diffusion model is trained through a unified multi-view-to-multi-view conversion framework based on the diffusion model. The conversion framework has a new self-supervised training strategy and a consistency and antagonism supervision strategy, and the strategies utilize an existing 2D single-view image converter and a 3D Gaussian splash technology to generate pseudo-truth values as supervision signals, so that view consistency and high-frequency details are enhanced; the multi-view consistency diffusion model trained by the conversion framework further comprises a potential multi-view consistency module, and the potential 3DGS module is used as a 3D representation of a bottom layer to promote information exchange across multiple views, so that 3D priori is introduced into the diffusion model to ensure view consistency. Finally, a joint optimization strategy is provided, and better balance between consistency and authenticity can be realized.
Owner:UNIV OF SCI & TECH OF CHINA

Hyperspectral and multispectral image fusion method based on wavelet feature fusion and comparative learning

The invention discloses a high-resolution hyperspectral image reconstruction method based on wavelet domain feature fusion and contrast learning, and belongs to the technical field of image fusion and super-resolution reconstruction. The method comprises the following steps: constructing a fusion network model comprising a wavelet transformation module, a cross-modal feature fusion module, a high-frequency contrast learning module and an image reconstruction module; performing end-to-end supervised training by using a training data set containing the low-resolution hyperspectral image and the high-resolution multispectral image; and after training is completed, inputting a test image pair to realize image reconstruction. According to the method, the detail retention capability is improved by combining wavelet decomposition and a directional fusion mechanism, the cross-modal high-frequency feature alignment capability is enhanced through comparative learning, a fusion image with high spatial resolution and high spectral consistency is finally generated, and the method is suitable for multi-modal image reconstruction tasks such as remote sensing, medical and natural images.
Owner:DONGHUA UNIV

Distributed optical fiber temperature sensing logging data blind denoising method and system based on physical self-supervised learning

The invention provides a distributed optical fiber temperature sensing logging data blind denoising method and system based on physical self-supervised learning. The method comprises the following steps: acquiring original noisy distributed temperature sensing (DTS) logging data, and generating a self-supervised training sample through a space-time alternating downsampling strategy by using the space-time coherence of the original noisy distributed temperature sensing (DTS) logging data; constructing a physical self-supervised blind denoising network model by using a simplified structure, and inputting a self-supervised training sample for training; in the training process, a multi-physical constraint loss function optimization model is introduced until a loss function converges, and a denoising model is obtained; and inputting to-be-processed complete DTS logging data into the denoising model to obtain denoised DTS logging data. According to the method, manual labeling and large-scale labeling of the data set are not needed, the inherent physical characteristics and structural information of the DTS data can be fully utilized, efficient and accurate blind denoising of the DTS logging data is achieved, and the problem that an existing deep learning denoising method needs to depend on a large amount of labeled data is solved.
Owner:NORTHEAST GASOLINEEUM UNIV

Citrus intelligent planting management-oriented large model field quantification and adaptive model deployment method

The invention belongs to the technical field of computer artificial intelligence, and relates to a citrus intelligent planting management-oriented large model field quantification and adaptive model deployment method, which comprises the following steps of: firstly, constructing a large model calibration data set and carrying out preprocessing, and inputting a Transform model to execute forward reasoning; then carrying out left multiplication rotation on a weight matrix of a to-be-quantized layer of the model and right multiplication rotation on an activation matrix, executing GPTQ quantization, calculating a dynamic adaptive smoothing factor of each channel of the activation matrix, executing normalization and symmetric quantization according to hidden dimension grouping, and generating a quantized Transform model; then obtaining citrus industry text data to construct a fine tuning instruction set, and performing supervised training on the quantitative model to generate a full-quantitative and full-precision model; and finally, by training a task complexity classifier, selecting a full-quantization or full-precision model as a target deployment model according to a task complexity level, so that efficient quantization and intelligent task adaptation of the model are realized.
Owner:YUNNAN UNIV