51 results about "Label free" patented technology

The invention discloses an unsupervised industrial defect detection method, system and device based on a multi-mode expert system. The unsupervised industrial defect detection method comprises the following steps: acquiring a label-free industrial defect image data set and a text cue word; inputting into a multi-modal expert system to obtain a corresponding prediction result; screening out a preliminary labeling result; filtering the preliminary labeling result based on a prior constraint to obtain a fine label; inputting the industrial defect image data set and the fine label into a self-supervised model for training, and outputting a pseudo label after training is completed; performing double filtering on the pseudo labels by adopting a dynamic threshold value and a prior constraint; inputting the industrial defect image data set and the pseudo label after the current training double filtering into the self-supervised model after the last training for re-training, outputting the pseudo label, and returning to execute the double filtering until the trained self-supervised model is obtained; and predicting an industrial defect image to be detected by adopting the trained self-supervised model to obtain a corresponding industrial defect detection result. And the detection accuracy and efficiency are improved.

The invention discloses an underwater in-situ fish label-free sample detection method and equipment. The method comprises the following steps: acquiring an in-situ image shot by a monocular camera of an underwater observation platform, and constructing an image-text structured knowledge base; extracting a training and verification data set of the detection model from the knowledge base, and dividing the data set into a closed set category and an open world category; receiving a natural language text instruction which is input by a user and is used for describing the to-be-detected data set, and generating a text feature vector of a target category; a targeting auxiliary model is obtained through vision-text semantic space training, dynamic interactive fusion is carried out on the visual features of the in-situ image and the text features of the category, and end-to-end joint optimization is carried out on the target model; and performing label-free detection on fishes appearing in the underwater in-situ image by using the optimized target model. According to the method, new species which are not seen during training can be effectively identified, cross-domain reasoning can be implemented on a label-free observation sample, and the retraining and maintenance cost is reduced.

The invention discloses a graph backdoor encoder defense method and device, and a readable storage medium. The method comprises the steps that at least two label-free enhanced data sets are generated based on a preset training data set, a to-be-processed encoder is trained based on the enhanced data sets to obtain a teacher encoder, and the training data set is a downstream data set or a subset of the downstream data set; defining identical attention operators in corresponding layers of the teacher encoder and the to-be-processed encoder, wherein the attention operators are used for outputting layer attention maps of corresponding encoder layers; calculating the distribution offset of the layer attention map of the teacher encoder and the layer attention map of the encoder to be processed in the same encoder layer; and fixing the parameters of the teacher encoder, and updating the parameters of the to-be-processed encoder based on the distribution offset. Compared with the prior art, through lightweight deployment, on the premise that the model precision is not reduced, the attack success rate of backdoor attack on graph self-supervised learning is effectively reduced, and the backdoor defense capability of the system is improved.

The invention discloses a semi-supervised image annotation method based on a limited label data set, and the method comprises the steps: taking a FixMatch frame as a basis, and integrating a learnable batch normalization module, a dual-scale parallel convolution module, a content and style separation dual-branch module and a dynamic residual gating module in a ResNet backbone network, the stability of feature extraction and the adaptive capacity to enhanced disturbance are improved. For a label-free sample, a multi-level pseudo-label fusion mechanism is provided, prediction distribution of weak, medium and strong enhanced views is synthesized, and high-confidence pseudo-labels are generated through confidence weighted fusion of multi-level enhanced views and comparison and screening with a category threshold. On the basis, a joint loss function composed of label supervision loss and pseudo label consistency loss is constructed, and a plurality of key control parameters in FixMatch + + are adjusted and optimized in a pre-experiment and grid search combined mode to obtain a group of optimal parameters of the model. Finally, a user inputs a label-free image into the trained FixMatch + + model, and the model can automatically generate a high-confidence pseudo label, so that the number of labeled samples in a limited labeled image set is increased, and the classification precision is improved. By implementing the method, the manual annotation cost can be reduced, and efficient and reliable support is provided for image analysis and recognition tasks.

The invention relates to the field of three-dimensional vision, in particular to a label-free three-dimensional point cloud segmentation method based on a visual large model, which comprises the following steps: acquiring three-dimensional point cloud data, and extracting a boundary point set according to the three-dimensional point cloud data in combination with curvature and normal vector to construct a target function; solving the objective function by using an optimization algorithm, selecting an optimal projection visual angle combination, and extracting two-dimensional features of all two-dimensional projection images and three-dimensional features of three-dimensional point cloud data by using a visual large model; performing consistency matching on the two-dimensional features and the three-dimensional features through a matching algorithm to obtain a plurality of matching results; acquiring a definition weight factor and a coverage rate weight factor to calculate an importance weight; fusing the two-dimensional features according to the weight factors to obtain overall fused two-dimensional features; and inversely mapping the integrally fused two-dimensional features to a three-dimensional space to realize three-dimensional point cloud unmarked segmentation. The three-dimensional point cloud segmentation method has the effect of realizing three-dimensional point cloud automatic segmentation without labels.

A particulate matter detection device takes holographic images of flowing particulate matter concentrated by a virtual impactor, which selectively slows down and guides larger particles to fly through an imaging window. The flowing particles are illuminated by a pulsed laser diode, casting their inline holograms on a CMOS image sensor in a lens-free mobile imaging device. The illumination contains three short pulses with a negligible shift of the flowing particle within one pulse and triplicate holograms of the same particle are recorded at a single frame revealing different perspectives of each particle. A deep neural network classifies the particles based on the acquired holographic images. The device was tested using different types of pollen and achieved a blind classification accuracy of 92.91%. This mobile and cost-effective device weighs ˜700 g and can be used for label-free sensing and quantification of various bio-aerosols over extended periods.

The invention discloses a data matching method, apparatus and device, and a storage medium. The method comprises the steps of constructing a to-be-discriminated data set and a training data set according to a plurality of sample pairs corresponding to a plurality of to-be-matched data sets; determining a plurality of pseudo label sample pairs and a plurality of to-be-discriminated sample pairs according to the initial discriminator and the to-be-discriminated data set; performing real label labeling on the plurality of to-be-discriminated sample pairs to obtain a plurality of labeled sample pairs, and updating the training data set in combination with a plurality of pseudo label sample pairs; and performing iterative training on the initial discriminator through the updated training data set, obtaining a sample label of each label-free sample pair according to the initial discriminator after the iterative training, and further performing data matching and storage on data samples existing in the data set. By means of the mode, the labeling cost is remarkably reduced, semi-supervised cooperative training is combined, the problem of data sample imbalance is effectively solved, the value of labeling data on model training is improved, and precise matching of complex data attributes is achieved.

The present invention discloses a mobile path planning method, device, robot and storage medium. The method comprises: when the robot triggers navigation resumption, determining the label type of the current label corresponding to the current position of the robot based on the collected image data; the label type includes at least one of: no label, legal label and illegal label; and planning the movement path of the robot based on the label type. By running the technical solution provided by the embodiment of the present invention, the problem of the robot passively leaving the originally planned movement path during autonomous movement, resulting in the interruption of the robot's navigation state and the inability to continue moving, which reduces the robot's movement efficiency and task execution efficiency, can be solved, thereby achieving the beneficial effect of improving the robot's movement success rate and movement efficiency.

The application belongs to the field of artificial intelligence model compression and edge deployment in intelligent operation and maintenance and fault diagnosis of power equipment, and discloses a transformer cooperative distillation incremental learning method and system based on time sequence consistency, which comprises the following steps: a teacher model is used to screen a no-label sample set to obtain a pseudo-label sample set, the pseudo-label sample set is combined with an original label sample set to obtain a distillation training sample set; a multi-mechanism cooperative distillation training scheme containing soft and hard label joint distillation, time sequence consistency distillation and multi-task distillation is constructed, and a student model is subjected to distillation training through the multi-mechanism cooperative distillation training scheme; and a cooperative distillation incremental learning scheme in which a cloud end continuously updates a teacher model to adapt to new multi-source monitoring data and a student model after edge distillation generates a pseudo-label to expand the distillation training sample set is constructed. The application can be used for realizing high-precision and low-cost training and continuous updating of a student model in a resource-limited terminal or an online scene.

The invention provides a few-label industrial process quality prediction method based on a DCMSViT model, and relates to the technical field of industrial process monitoring, and the method comprises the steps: carrying out the preprocessing of historical data, and dividing the historical data into a labeled sample set and an unlabeled sample set; then, a dynamic collaborative regression module is utilized to generate pseudo labels for unlabeled samples based on labeled samples, and high-confidence pseudo label samples are screened out through a dynamically calculated confidence threshold, so that a labeled training set is expanded; then, the expanded labeled sample set and the remaining unlabeled sample set are input into a multi-scale visual Transform module together for training, and the multi-scale visual Transform module is used for extracting global feature vectors of the data so as to carry out quality prediction; and finally, the trained DCMSViT model is utilized to realize real-time and online prediction of the key quality variables of the industrial process. According to the method, a small amount of label data and a large amount of label-free data are effectively utilized, and the accuracy of industrial process quality prediction and the model generalization ability in a small-label scene are remarkably improved.

The present disclosure relates to a model training method, an instant pushing method, a device, a medium and an electronic device, and belongs to the technical field of computers, and can realize model training in an end intelligent scene. A model training method based on federated learning comprises: multiple first participants with labels, the same features and different samples, encrypting the label values possessed by the multiple first participants and transmitting the encrypted label values to a second participant without labels, the second participant possessing all the samples of the first participants but having different features from the first participants; the second participant determining a second gradient based on the encrypted label values and feature values of the features possessed by the second participant and transmitting the second gradient to the first participants; the first participants determining a first gradient and a first histogram based on the feature values of the features possessed by the first participants and the label values possessed by the first participants and transmitting the first gradient and the first histogram to the second participant; the first participants determining a first optimal split point based on the second gradient and transmitting the first optimal split point to the second participant; and the second participant determining a global optimal split point based on the first gradient, the first histogram and the first optimal split point and transmitting the global optimal split point to the first participants.

An optical system includes an optical resonant cavity, an optical source, an optical detector, and a signal processing circuit. The optical source is arranged to provide a source beam of light to be at least partially coupled into the optical resonant cavity. The optical detector is arranged to detect light from the source beam of light after the source beam of light has coupled into the optical resonant cavity to provide a detection signal. The signal processing circuit is configured to communicate with the optical detector to receive the detection signal. The optical resonant cavity has a bioconjugatable lipid membrane on a surface thereof. The bioconjugatable lipid membrane is functionalized to capture a specific biomolecule, and the signal processing circuit is further configured to determine a presence of the specific biomolecule when captured by the functionalized bioconjugatable lipid membrane based on processing the detection signal.

The invention relates to a vibration meter error monitoring and calibrating method and system based on data analysis, and the method comprises the steps: obtaining a plurality of paired original vibration signals, and screening and marking credible samples and suspicious samples; calculating a first error value of the credible sample, generating a first training set with a credible label according to the first error value, and training a first error model; predicting the suspicious sample according to the first error model, and generating a pseudo label; calculating the prediction uncertainty of a pseudo label, screening a pseudo label sample, combining the pseudo label sample with the first training set, generating a second training set, and training a second error model; inputting the vibration signal to be calibrated into the second error model to obtain a real-time error; and the real-time error is calibrated. According to the technical scheme, the true label is generated by using the high-credibility sample, a large amount of label-free field data is converted into available training data by means of pseudo label self-training, the model accuracy is improved, and therefore the error monitoring and calibration precision of the vibration meter is improved.

A method, device and system (10) for labeling data, relating to the field of computers, effectively improving the efficiency of labeling data. The method is applied to a computing device (20), comprising: determining a target control parameter based on first labeled data and first unlabeled data; sending the target control parameter to a quantum annealing device (30), the target control parameter being used to instruct the quantum annealing device (30) to perform quantum annealing to obtain a target annealing result, wherein the target annealing result includes the state of quanta in a quantum group (51, 52, 53, 54, 55, 56, 57, 58) corresponding to the first unlabeled data, and the state of quanta in the quantum group (51, 52, 53, 54, 55, 56, 57, 58) corresponding to the first unlabeled data is used to characterize the label of the first unlabeled data.

The application discloses a pseudo-label model training method and device, a storage medium and electronic equipment. The method comprises the following steps: obtaining a plurality of sample communication relationship data with added sample labels; using a first classification model to analyze the sample communication relationship data, and generating a first classification label, wherein the first classification model is trained using clean label data; using a second classification model to analyze the sample communication relationship data, and generating a second classification label, wherein the second classification model is trained using mixed data, and the mixed data comprises clean label data, noise label data and unlabeled data; determining that the difference between the sample label and the second classification label is a first difference, and the difference between the first classification label and the second classification label is a second difference; and using a preset loss function model to analyze the first difference and the second difference, and determining a pseudo-label model. The application solves the technical problem that unlabeled data cannot be used for model training.

Provided are a reinforcement learning-based label-free six-dimensional object pose prediction method and apparatus. The method includes: obtaining a target image to be predicted, the target image being a two-dimensional image including a target object; performing pose prediction based on the target image by using a pre-trained pose prediction model to obtain a prediction result, the pose prediction model being obtained by performing reinforcement learning based on a sample image; and determining a three-dimensional position and a three-dimensional direction of the target object based on the prediction result. The pose prediction model is trained by introducing reinforcement learning, the pose prediction is performed based on the target image by using the pre-trained pose prediction model, and thus the problem of six-dimensional object pose estimation based on two-dimensional images can be solved in the absence of real pose annotation, which ensures the prediction effect of label-free six-dimensional object pose prediction.

The embodiment of the invention provides a robot control method, electronic equipment, a storage medium and a program product, a UWB sensing module is deployed on a robot, the robot control method comprises the steps that the current mode of the UWB sensing module is determined, the current mode is a label mode or a label-free mode, the UWB sensing module senses a UWB label in the label mode, and the UWB label is sent to the electronic equipment; in the no-label mode, the UWB sensing module does not sense the UWB label; determining a first interaction behavior according to the current mode and the collected data of the UWB sensing module; and executing the first interaction behavior. Therefore, the accuracy of the interactive behavior decision of the robot is improved.

The application discloses a kind of label-free inference enhancement methods based on generator-verification collaborative evolution, which utilizes large language model as generator and verifier simultaneously: first, generator generates result set multiple times on inference query inference, and drafts pseudo-label to divide positive and negative sample groups through majority vote;Subsequently, the verifier verifies the positive sample to form a positive verification set, and generates a verification result for the negative sample to form a negative verification set;Based on the positive and negative sets, contrast training samples are constructed to correct errors and optimize the inference and verification capabilities of the model. The optimized model can be directly used for inference and verification of target queries. Experiments show that on mathematical reasoning and cross-domain question answering datasets, this method significantly improves inference and verification accuracy, while training stability is superior and has outstanding cross-distribution generalization capability.

The application relates to a remote sensing image cross-domain migration classification method for a label-free target area, comprising the following steps: acquiring multi-source remote sensing data covering a region; constructing an adversarial domain self-adaptive network; calculating a classification loss and a domain discrimination loss; constructing an adversarial training total loss function, and reversely propagating network parameters after dynamically adjusting a weight coefficient to update the network parameters; inputting target domain images into a trained feature extractor and a classifier, and finally outputting a refined classification result map. The application has the beneficial effects that the application enhances the multi-dimensional representation capability of a model for a complex geographical environment, overcomes the limitation of a single data source, and provides a more robust feature basis for cross-domain migration classification.

The application belongs to the field of electrochemistry, and relates to tumor protein P53 gene detection, in particular to a label-free double-color test strip, a kit and a preparation method thereof for tumor protein P53 gene detection. The application belongs to a novel LFA method, which combines DNA hybridization chain reaction with the electrostatic adsorption principle of test line / control line, selects common and cost-effective bovine serum albumin as the test line, utilizes the difference in the adsorption capacity of BSA to double-stranded DNA and nano-gold, and the different flow rates of different molecules on the NC membrane to complete the detection of p53 at different concentrations. The test line is constructed by positively charged PDDA to ensure the effectiveness of the LFA. Meanwhile, the detection principle of a liquid colorimetric sensor is combined, and the double-color development greatly reduces the detection limit of the test strip. The sensor is label-free throughout, and has high analytical performance in terms of sensitivity, selectivity and practicability. The p53 gene is detected on the lateral flow test strip for the first time.

The invention discloses an underwater sound target identification method and system based on soft label guidance and domain adversarial fine tuning, and the method comprises the steps: employing a labeled underwater sound data set, an unlabeled underwater sound data set, and a source domain general audio data set; a joint loss function including classification loss, soft label distillation loss and domain adversarial loss is constructed to assist the knowledge distillation process of the teacher model to the student model; meanwhile, dynamic convolution and dynamic activation functions are introduced into a dynamic convolution feature extraction module in the student model, so that the adaptive modeling capability of the model to input signal characteristics is enhanced; besides, a multi-layer enhanced long short-term memory network module and a residual connection mechanism are arranged in a feature enhancement module, and an index gating mechanism and a new memory mixing mode are introduced into the enhanced long short-term memory network module, so that the problem of gradient disappearance or explosion in a deep network is solved; and the modeling capability of the long-time sequence dependency relationship is effectively enhanced.

This application discloses a method, apparatus, electronic device, medium, and program product for pseudo-labeling. The pseudo-labeling method includes: obtaining a real label sample set; labeling an unlabeled sample set as an initial pseudo-label sample set based on a first labeling model constructed from the real label sample set; dividing the initial pseudo-label sample set into a first pseudo-label sample set and a second pseudo-label sample set; re-labeling the second pseudo-label sample set using a second labeling model jointly constructed from the real label sample set and the first pseudo-label sample set to obtain a third pseudo-label sample set; calculating the label difference value between the pseudo-labels labeled in the second and third pseudo-label sample sets; and filtering the target pseudo-label sample set by removing samples from the second and third pseudo-label sample sets whose label difference value is greater than a preset label difference threshold. This application solves the technical problem of low accuracy in pseudo-labeling in the prior art.

A method of performing cell assays, comprising: inputting in a computing system a digital refractive index (RI) image of a sample containing a plurality of cells, applying a segmentation algorithm in said computing system to process said digital RI image configured to locate and define an outer boundary of each cell of said plurality of cells, applying in said computing system RI values from the RI image to the segmented cells, calculating in said computing system from the RI values, metrics including any of composition, structure and shape of each segmented cell, evaluating the metrics with a machine learning module in said computing system to classify a physiological state of each of the cells.

The present application relates to the technical field of computer vision and image processing, and discloses a remote sensing weakly supervised fine-grained target detection and recognition method and device, based on a general text prompt corresponding to a small amount of labeled remote sensing data samples and a large amount of unlabeled remote sensing data samples, by extracting the geometric features of the samples and the cross-modal features representing the visual text differences, combining the fine-grained class labels of the labeled remote sensing data samples, prior knowledge prototypes of various fine-grained classes are constructed; then, the prior knowledge prototypes of various fine-grained classes are used to construct fine-grained soft labels of the unlabeled remote sensing data samples, which are used as supervision signals to realize the training of the model, solve the cost consumption problem of fine-grained labeling, improve the label labeling efficiency of the unlabeled remote sensing data samples, and further improve the model training efficiency and target recognition efficiency.

The invention provides a target recognition system based on computer vision, and relates to the technical field of computer vision, and the system comprises a data preprocessing module which is used for preprocessing an input image and generating standardized image data, and an unsupervised learning module which carries out target feature learning through self-supervised learning, reduces the dependence on manual annotation data, and improves the recognition efficiency. A target feature extraction and classification model is optimized by using label-free data, a feature extraction module extracts image features through a visual converter, and self-adaptive local and global attention mechanisms are combined. According to the target recognition system based on computer vision, through combination of self-supervised learning and automatic annotation generation, dependence on manual annotation data is remarkably reduced. Through self-supervised learning, the features can be automatically extracted from the label-free data and the labels can be generated, so that the cost of data labeling is reduced, and the adaptability of the system to a new field or a new task is improved.

The invention provides a label replacement method and device, electronic equipment and a storage medium, relates to the technical field of big data processing, and can accurately and efficiently replace labels in batches. A first label data set of a first version and a second label data set of a second version are obtained. Each label data set comprises a plurality of pieces of corresponding label data and label information corresponding to each piece of label data, each piece of label data comprises a label value of a fixed label, the label information indicates label value conditions of a plurality of fixed labels in the label data, and the label value conditions comprise label values and label-free values. Deleting marks are added to all label values of the first part data and the third part data in the multiple pieces of first label data, classification marks are added to all label values of the second part data in the multiple pieces of first label data based on first mark information and second mark information, and multiple pieces of reconstructed first label data are obtained; and updating the tags in the database based on the reconstructed first tag data.

The application provides a kind of telecommunication anomaly detection method and detection device.The method comprises: obtaining the social relationship information and portrait feature information of each user in personnel relationship heterogeneous graph, obtaining the fusion feature information and relationship feature information of each user according to label information, portrait feature information and social relationship information;According to fusion feature information and relationship feature information, adopt neighborhood aggregation algorithm, obtain the node feature information of label user;Based on semi-supervised learning mechanism, according to social relationship information and node feature information, through improved attention mechanism model, obtain the anomaly probability of each user, to realize through label propagation algorithm, the label information of label user is propagated to unlabelled user, and anomaly detection is completed.The method of the application utilizes the context information of multiple relationships in heterogeneous graph and the characteristics of semi-supervised learning, effectively improves the detection accuracy and adaptability of the model in the label scarce scene.

The application discloses a semi-supervised image labeling method FixMatch++ based on a limited label data set, which is based on the FixMatch framework, and four modules, including a learnable batch normalization, a double-scale parallel convolution, a content and style separation double branch, and a dynamic residual gate, are integrated in a ResNet backbone network to improve the stability of feature extraction and the adaptability to enhanced perturbations. For unlabeled samples, a multi-level pseudo label fusion mechanism is proposed, the prediction distribution of three types of enhanced views, including weak, medium and strong, is integrated, high-confidence pseudo labels are generated by multi-level enhanced view confidence weighted fusion and comparison with a class threshold, and a joint loss function composed of a labeled supervised loss and a pseudo label consistency loss is constructed. Through pre-experiments combined with grid search, a group of optimal parameters of the model are obtained by adjusting and optimizing a plurality of key control parameters in FixMatch++. Finally, a user inputs an unlabeled image into the trained FixMatch++ model, and the model can automatically generate high-confidence pseudo labels, thereby expanding the number of labeled samples in the limited labeled image set and improving the classification accuracy. The implementation of the method can reduce the cost of manual labeling and provide efficient and reliable support for image analysis and recognition tasks.

Provided are methods and devices for the label free detection of analytes in solution, including analytes suspended in a biological fluid. A field effect transistor (FET) is positioned in close proximity to a paired set of reference electrodes and the reference electrodes electrically biased to provide desalting and a stable gate voltage to the FET. In this manner, charged ions are depleted in the sensing region of the sensor and device sensitivity to analyte detection improved by the removal of charge that otherwise interferes with measurement. Also provided are methods and systems providing increased in reference electrode surface area and / or decrease in droplet volume to further improve label-free detection of analytes.

The invention discloses an unmanned aerial vehicle rotor bearing fault diagnosis method and system based on multi-source data, and relates to the technical field of bearing fault diagnosis, and the method comprises the steps: obtaining a to-be-diagnosed sample during the operation of an unmanned aerial vehicle rotor bearing; extracting a multi-source fusion implicit code feature vector, inputting the multi-source fusion implicit code feature vector into a fault diagnosis learning device, and outputting a fault diagnosis result; the training method of the feature extractor and the fault diagnosis learner comprises the following steps: collecting labeled samples and unlabeled samples; constructing an integrated model; performing expert marking on K unlabeled samples with the highest comprehensive score, and supplementing the K unlabeled samples to a set of labeled samples; predicting a false label for the unmarked label-free sample and obtaining a false label sample; the pseudo label samples are incorporated into a training set, wherein the training set further comprises label samples and marked non-label samples; and training the integrated model. According to the method, the problems of insufficient utilization of multi-source features, serious waste of unlabeled samples and insufficient representativeness of the unlabeled samples are solved.