14results about How to "Reduce training overhead" patented technology

The invention discloses a facial acne grading method based on collaborative mapping multi-scale self-distillation, is applied to the field of computers, and aims to solve the problem of low accuracy of acne severity grading in the prior art. According to the method, the convolutional neural network model is trained by adopting a self-distillation architecture, and a novel distillation module optimization training process is provided in combination with the characteristics of acnes, so that the model can notice the uniqueness of acne images, and the severity grading precision of the model for facial acnes is improved. The method can automatically identify the acne features and grade the severity of the acne features, assists doctors in diagnosis and treatment, and accelerates the healing period of the acne.

The invention is suitable for the technical field of visual language models, and provides a distillation learning method of an open vocabulary target detection model, which comprises the following steps: based on a pre-trained candidate frame extraction model, obtaining a pseudo tag of a to-be-detected picture, cutting the to-be-detected picture according to a pseudo tag region, obtaining a pseudo tag region image, and obtaining an open vocabulary target detection model; the pseudo label is a candidate frame which is not overlapped with the label frame of the known class; based on a CLIP visual encoder, obtaining visual features of the pseudo label area image; on the basis of a CLIP text encoder, a text category label generation method is adopted, and text features of the pseudo label area image are obtained; and based on the visual features and the text features, performing knowledge distillation learning on the target detection model by adopting a bisymmetric distillation method, so that the target detection model learns the visual features of the CLIP visual encoder and the text features of the CLIP text encoder. And the generalization ability of the target detection model is improved.

The invention discloses an edge terminal-oriented memory efficient model fine tuning method and system, which realize decoupling of a backbone network and a fine tuning process by constructing a parallel side network module, and avoid video memory occupation caused by backbone gradient return. A double-adapter module is arranged, modeling is carried out on same-layer features and cross-layer context information, and the feature expression precision is improved. And constructing a feature fusion module, and performing adaptive weighting on different path outputs through learnable gating. A backbone grouping module is integrated, dynamic grouping is carried out on a backbone network based on interlayer similarity, and redundant modules and calculation overhead are reduced. And through the fine tuning execution module, only back propagation and parameter updating are carried out on the side network, and a trunk freezing state is kept, so that the memory and training cost is reduced. According to the method, the memory efficiency and the training speed of the edge fine adjustment process are improved, high-precision model self-adaption is achieved with extremely low calculation burden, and application in the fields of cloud edge collaborative intelligence and the like of unmanned aerial vehicles, robots, vehicle-mounted terminals and the like is effectively supported.

The invention provides a large-model multi-language enhancement training method capable of continuously expanding experts, which comprises the following steps: step 1, extracting an original FFN module in a large-scale language model LLM to be trained and segmenting the original FFN module into a plurality of new fine-grained FFN modules as fine-grained experts; 2, setting a fine-grained router, and selecting a preset number of newly-added fine-grained experts according to a preset rule to obtain the output of the fine-grained router; 3, setting a parent router, controlling the weight between the output of the original FFN module and the output of the fine-grained router, and calculating the final output; 4, freezing an original FFN module, and independently training the fine-grained expert; step 5, freezing an original FFN module, adding the newly added fine-grained expert, and training the newly added fine-grained expert; step 6, freezing all other parameters, and only training a parent router; and 7, continuously repeating the step 4 to the step 6 to realize large-model multi-language enhancement training of sustainable extension experts.

A method, system, and apparatus for spectrum sharing in a massive multiple-input multiple-output (MIMO) network are disclosed. According to one aspect, there is provided a method in a secondary network node of a secondary network, the secondary network node being configured to communicate with a plurality of secondary users. The method includes performing channel estimation of a primary user of the primary network during a learning phase consistent with a training phase of the primary network. The method further includes determining a beamformer and a power allocation based at least in part on the channel estimate to maximize at least one of a weighted uplink data rate and a weighted downlink data rate under constraints with respect to a data rate of the primary network.

This invention belongs to the interdisciplinary field of artificial intelligence and cheminformatics, and provides a method, inference method, and apparatus for constructing a molecular multimodal large language model based on parameter space alignment. The method includes: constructing an instance set; constructing a molecular multimodal large language model, including an adaptive weight generator, a graph neural network encoder, and a large language model; training the molecular multimodal large language model using the instance set to update the parameters of the adaptive weight generator; the graph neural network encoder extracting node-level feature representations of the molecular structure diagram; the adaptive weight generator obtaining the low-rank weight update amount of the target weight component in the large language model based on the node-level feature representation, and injecting the low-rank weight update amount into the original weights of the target weight component; and the large language model after injecting the low-rank weight update amount generating an actual text response based on the input training text command. By integrating the molecular structure into the parameter layer of the large language model, deep perception of the molecular structure is achieved without changing the length of the input sequence.

The application discloses an improved ELM speech enhancement method and device for noise reduction, and belongs to the field of speech signal processing; specifically, first, a noisy speech signal and a clean speech signal are acquired to construct training samples; meanwhile, an improved ELM speech enhancement network is constructed, the training samples are used for training, and a network weight matrix is saved; then, a new noisy speech signal is acquired, input into the trained enhancement network to output a noise-reduced enhanced speech signal; the device comprises an audio acquisition module, an offline training module, an online running module and an audio playing module; the audio acquisition module acquires speech signal samples used for training and inputs the offline training module to train the improved ELM speech enhancement network and save the network weight matrix; a new noisy speech signal is acquired and input into the online running module to directly output a noise-reduced enhanced speech signal; and the audio playing module is used for playing. The application reduces training cost and has lower processing time delay.

The invention relates to a multi-mode millimeter wave beam prediction method based on multi-task learning, and belongs to the technical field of millimeter wave communication. The method comprises the following steps: converting a beam prediction task into a deep learning optimization task based on a geometric channel model in a dynamic communication scene; preprocessing the image, the three-dimensional point cloud and the user motion information acquired by the base station to complete region-of-interest extraction, point cloud downsampling and space coordinate conversion; through a cross-modal gating fusion module, adaptively extracting and carrying out weighted fusion on the multi-modal features; and constructing a multi-task learning framework, cooperatively training a beam prediction main task and blocking prediction and reflection intensity prediction auxiliary tasks, correcting an optimal beam probability by using physical constraint information output by the auxiliary tasks, and selecting an optimal beam. According to the method, the beam training overhead and the communication delay are remarkably reduced, the environmental limitation of single-mode sensing is effectively overcome, and the prediction robustness of the system in a complex dynamic scene is enhanced while the beam prediction precision is improved.

The application discloses a method and device for single-sample action recognition based on WiFi, which physically models the WiFi action recognition scene, generates virtual action data from basic actions, thereby enriching the data set and reducing the cost of collecting real data. Based on supervised learning and meta-learning, a single-sample action recognition framework is designed and implemented. The framework uses a traditional supervised learning mechanism for first-stage training on a virtual action data set, uses a single-sample meta-learning mechanism for second-stage training on a basic action data set, and uses a single-sample meta-learning mechanism for model fine-tuning on a single-sample data set of a new action, thereby obtaining a model capable of accurately recognizing the new action. The training of the two stages only needs to be performed at the initial deployment, and if there is a need to change the action type subsequently, only the model fine-tuning needs to be performed by using a single-sample data of a new action, thereby significantly reducing the model training cost, being highly scalable, and being applicable to actual application scenarios.

The present application belongs to the field of artificial intelligence, and relates to a text classification method, device, computer equipment and storage medium, the method comprising: segmenting a training text to obtain a plurality of semantic blocks; inputting each semantic block into an initial classification value assessment model to obtain a classification value score; screening the semantic blocks according to the classification value score to obtain a semantic block queue, and then inputting the initial text classification model to obtain a classification prediction result; determining the semantic block label of each semantic block in the semantic block queue; calculating a first loss based on the semantic block label and the classification value score, and calculating a second loss based on the classification prediction result and the classification label of the training text; adjusting the initial classification value assessment model according to the first loss to obtain a classification value assessment model, and adjusting the initial text classification model according to the second loss to obtain a text classification model; processing the text to be classified through the classification value assessment model and the text classification model to obtain a text classification result. The present application improves the accuracy of text classification.

The application relates to a training sample screening method and device based on global semantic modeling. The method comprises the following steps: obtaining at least one training sample set, each training sample set comprising at least one training sample; for each training sample set, inputting each training sample into an artificial intelligence model to obtain a response result of each training sample; the response result is obtained by at least performing self-attention calculation and nonlinear transformation calculation on the training sample by the artificial intelligence model; comparing whether the response result of each training sample meets corresponding labeled data of each training sample to determine a response accuracy of the artificial intelligence model on the training sample set; if the response accuracy meets a preset condition, the training sample set is determined as a target post-training sample set; and the target post-training sample set is used for performing post-training on the artificial intelligence model. By using the method, high-quality and low-cost post-training can be realized.

The application discloses an adversarial knowledge distillation method and system based on feature semantic guidance and feature orthogonalization, which firstly acquires an image classification dataset, extracts text features, and constructs a semantic feature space.Secondly, a knowledge distillation framework including a teacher model, a student model and a projection head is constructed, the input of the teacher model and the student model is an image in the dataset, and the output is an image category prediction result. Then, the student model parameters are frozen, the projection head is updated through momentum tracking, in the feature level semantic adversarial sample generation stage, all network parameters are frozen, and normalized disturbance is constructed to obtain adversarial features. Finally, in the student model multi-objective joint optimization stage, the teacher model and the two projection heads are fixed, the student model parameters are updated, the classification loss, the distillation loss, the consistency loss and the orthogonalization loss are introduced, and optimization is completed. The application improves the fine-grained discrimination and generalization ability of the student model image classification, and does not introduce additional reasoning overhead.

The invention discloses a privacy protection image classification model training method and an image classification method and device, a privacy protection image classification model comprises a teacher image classification sub-model and a student image classification sub-model, and the image classification method comprises the following steps: obtaining to-be-classified image data; classifying and identifying the to-be-classified image through the privacy protection image classification model, and obtaining the classification of the to-be-classified image on the premise of privacy protection; the privacy protection image classification model is obtained through the training method of the privacy protection image classification model. The device comprises a privacy protection image classification model training device and an image classification device. According to the invention, classification and identification of the to-be-classified image are realized through the privacy protection image classification model.

The present application relates to the technical field of computer vision, in particular to a pig part zero-label recognition method based on discrete Morse theory. A video frame sequence containing pigs is obtained, and instance segmentation of the pigs is performed based on a text prompt through a visual basic model to obtain a binary mask and image embedding features; an Euclidean distance transform terrain field is predicted according to the image embedding features and the background area is removed; the Euclidean distance transform terrain field is taken as a discrete Morse function to determine topological critical points and persistent homology values; an initial skeleton is obtained by skeleton thinning the binary mask, and the terminal branches are pruned according to the persistent homology values to obtain a pig topological skeleton; the head, tail and leg are identified according to the pig center, end points in the pig topological skeleton, head direction and pig body axis to obtain a pig part recognition result. The present application does not require manual key point labeling, can reduce deployment cost and improve cross-scene applicability.