Abstract: The method in this application includes: First, a target image including a to-be-detected object may be obtained, and the target image is input to a target model. Then the target model may perform feature extraction on the target image to obtain a first feature, and further perform feature extraction on the first feature to obtain a second feature. Then the target model may perform first fusion on the first feature and the second feature to obtain a first fusion result. Then the target model may enhance the first feature and the second feature based on the first fusion result to obtain an enhanced first feature and an enhanced second feature. Finally, the target model may perform detection by using the enhanced first feature and the enhanced second feature to obtain location information of the object in the target image.

Abstract: This disclosure relates to the artificial intelligence field, and discloses a data processing method, including: obtaining a first query corresponding to a first neural network and a second query corresponding to a second neural network, where the first query is a query obtained by maximizing an information entropy of a query corresponding to the first neural network, the first neural network is a model obtained by compressing the second neural network, and the first neural network and the second neural network are used for object detection; determining a first loss based on the first query and the second query, where the first loss indicates to minimize an information difference between the second query and the first query; and updating the first neural network and the first query based on the first loss.

Abstract: This disclosure discloses methods, apparatuses, and systems related to perception networks. In an implementation, a method comprises: performing convolution processing on input data to obtain M target feature maps, performing convolution processing on M1 target feature maps in the M target feature maps to obtain M1 first feature maps, wherein M1 is less than M, processing M2 target feature maps in the M target feature maps to obtain M2 second feature maps, wherein M2 is less than M, and concatenating the M1 first feature maps and the M2 second feature maps to obtain a concatenated feature map.

Abstract: Aspects of the disclosure provide a method for fabricating a semiconductor device having an first stack of alternating insulating layers and sacrificial word line layers arranged over a substrate, the first stack including a core region and a staircase region. The method can include forming a first dielectric trench in the core region of the first stack, forming a second dielectric trench that is adjacent to and connected with the first dielectric trench in the staircase region of the first stack, and forming dummy channel structures extending through the first stack where the dummy channel structures are spaced apart from the second dielectric trench.

Abstract: A method and an apparatus for training a model, an electronic device, and a storage medium are provided. The method includes: dividing a training image into blocks, to obtain a plurality of first image blocks; performing occlusion on the plurality of first image blocks, to obtain a plurality of second image blocks; inputting a feature vector of each second image block into an encoding network to perform encoding, to obtain a plurality of encoding features corresponding to a plurality of network blocks; inputting each encoding feature into a decoding network corresponding to each encoding feature to perform image reconstruction, to obtain a reconstructed image corresponding to each decoding network; and training the model based on the reconstructed image corresponding to each decoding network and supervision information corresponding to each decoding network.

Abstract: This application discloses a data processing method relating to the field of artificial intelligence, and is for an activation unit in a neural network. The activation unit includes a plurality of processing branches. The method includes: performing activation processing on input data via each processing branch of the plurality of processing branches based on a corresponding activation function, to obtain a plurality of processing results; and fusing the plurality of processing results, to obtain a target processing result. In this application, a nonlinearity enhancement activation function is obtained by fusing a plurality of activation functions, to increase nonlinearity of the activation function, and further improve network accuracy.

Abstract: Systems and methods for providing deep learning models capable of performing joint representation learning and new category discovery on a mixture of labeled and unlabeled data, which may include single- and multi-modal data. In some examples, a flexible end-to-end framework uses unified contrastive learning on labeled and unlabeled data based on both instance discrimination and category discrimination, and further uses Winner-Take-All hashing to generate a pseudo-label based on the similarity between each pair of unlabeled data points that can be used to train the model to generate clustering assignments for each unlabeled data point. In some examples, the unified contrastive learning may be further based on cross-modal discrimination.

Abstract: Provided are an adaptive reclosing method and apparatus for a distribution network, a medium, and a device, which relate to the technical field of automatic control for distribution networks. Firstly, a voltage threshold for reclosing start-up is set based on power of a load and a distributed renewable energy source that are connected in a downstream direction of a circuit breaker of a distribution network before the distribution network fails. Then, after a fault occurs in the distribution network, a positive sequence voltage amplitude and its change rate are calculated. Finally, disconnection and fault statuses of a distributed renewable energy source network are determined based on the positive sequence voltage amplitude and its change rate, and reclosing is performed based on a preset corresponding delay for different situations.

Abstract: A model training method includes performing sampling on the target model to obtain a submodel of the target model, and a quantity of feature transformation layers of the submodel is less than a quantity of feature transformation layers of the target model, and/or a size of a weight matrix of at least one of feature transformation layers of the submodel is less than a size of a weight matrix of a corresponding feature transformation layer of the target model; augmenting the submodel to obtain an augmented model; and training the augmented model to obtain a trained augmented model.

Abstract: This application relates to an image recognition technology in the field of computer vision in the field of artificial intelligence, and provides an image classification method and apparatus. The method includes: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain a candidate output feature map of M channels, where M is a positive integer; performing matrix transformation on the M channels of the candidate output feature map based on N matrices, to obtain an output feature map of N channels, where a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classify the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.

Abstract: The present disclosure relates to methods implemented by using an image processing model. One example method includes performing feature extraction on an input image to obtain a first feature map, where the input image includes N image blocks, and N?2, aggregating at least two image blocks in the input image to obtain a second feature map, where positions of the at least two image blocks are correlated, and obtaining an output image based on the first feature map and the second feature map.

Abstract: This application relates to a data processing method and apparatus, and a storage medium. The method includes: extracting a feature sequence of target data, where the feature sequence includes T input features, T is a positive integer, and t?[1, T]; obtaining T hidden state vectors based on a recurrent neural network, where a tth hidden state vector is determined based on a (t?1)th input feature, a (t?1)th hidden state vector, and a (t?1)th extended state vector, and the (t?1)th extended state vector is obtained by performing lightweight processing based on the (t?1)th hidden state vector; and obtaining a processing result of the target data based on the T hidden state vectors by using a downstream task network.

Abstract: A neural network parameter quantization method includes obtaining a parameter of each neuron in a to-be-quantized model to obtain a parameter set, clustering parameters in the parameter set to obtain types of classified data, and quantizing each type of classified data in the types of classified data to obtain at least one type of quantization parameter, where the at least one type of quantization parameter is used to obtain a compression model, and precision of the at least one type of quantization parameter is lower than precision of a parameter in the to-be-quantized model.

Abstract: This application discloses a visual task processing method and a related device thereof. A to-be-processed image can be processed using a target model, and features outputted by the target model can remain diversified, to help improve processing precision of a visual task for the to-be-processed image. The method in this application includes: obtaining a to-be-processed image; processing the to-be-processed image using a target model, to obtain a feature of the to-be-processed image, where the target model includes a first module and a second module connected to the first module, the first module includes a graph neural network, and the second module is configured to implement feature transformation; and completing a visual task for the to-be-processed image based on the feature of the to-be-processed image.

Abstract: The present application discloses an image generation method, a neural network compression method, and a related apparatus and device in the field of artificial intelligence. The image generation method includes: inputting a first matrix into an initial image generator to obtain a generated image; inputting the generated image into a preset discriminator to obtain a determining result, where the preset discriminator is obtained through training based on a real image and a category corresponding to the real image; updating the initial image generator based on the determining result to obtain a target image generator; and further inputting a second matrix into the target image generator to obtain a sample image. Further, a neural network compression method is disclosed, to compress the preset discriminator based on the sample image obtained by using the foregoing image generation method.

Abstract: This application relates to an image recognition technology in the field of computer vision in the field of artificial intelligence, and provides an image classification method and apparatus. The method includes: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain a candidate output feature map of M channels, where M is a positive integer; performing matrix transformation on the M channels of the candidate output feature map based on N matrices, to obtain an output feature map of N channels, where a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classify the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.

Abstract: This invention relates generally to compositions and methods for increasing the efficacy of immunotherapies and vaccines. In particular, the present invention relates to compositions comprising one or more metabolites (derivatives, prodrugs, or pharmaceutical salts thereof), and related methods of increasing the efficacy of immunotherapies and vaccines through administration of such compositions.

Abstract: Aspects of the disclosure provide a method for fabricating a semiconductor device having an first stack of alternating insulating layers and sacrificial word line layers arranged over a substrate, the first stack including a core region and a staircase region. The method can include forming a first dielectric trench in the core region of the first stack, forming a second dielectric trench that is adjacent to and connected with the first dielectric trench in the staircase region of the first stack, and forming dummy channel structures extending through the first stack where the dummy channel structures are spaced apart from the second dielectric trench.

Abstract: In one aspect, a system for dispersing particles in a fluid of a fluid container includes one or more permanent magnets, one or more electric coils, and/or one or more electrodes. The one or more permanent magnets, one or more electric coils, and/or one or more electrodes are configured to disperse the particles in the fluid of the fluid container.