Abstract: A processing apparatus includes a collection module and a training module, the training module includes a backbone network and a region proposal network (RPN) layer, the backbone network is connected to the RPN layer, and the RPN layer includes a class activation map (CAM) unit. The collection module is configured to obtain an image, where the image includes an image with an instance-level label and an image with an image-level label. The backbone network is used to output a feature map of the image based on the image obtained by the collection module.

Abstract: This application relates to a model migration method in the field of artificial intelligence, including: obtaining sample data of a target task, where the sample data includes a plurality of image samples; separately evaluating N pre-trained models based on the sample data, to obtain N evaluation values, where the evaluation value represents adaptation between the pre-trained model and the target task, and N?2; determining K pre-trained models from the N pre-trained models based on the N evaluation values, where the K pre-trained models are models corresponding to first K evaluation values obtained by sorting the N evaluation values in descending order, and 1?K?N; and processing the sample data based on the K pre-trained models to obtain a target model used to process the target task, where the target model includes the K pre-trained models.

Abstract: Embodiments of the present invention provide a machine learning model training method, including: obtaining target task training data and N categories of support task training data; inputting the target task training data and the N categories of support task training data into a memory model to obtain target task training feature data and N categories of support task training feature data; training the target task model based on the target task training feature data and obtaining a first loss of the target task model, and separately training respectively corresponding support task models based on the N categories of support task training feature data and obtaining respective second losses of the N support task models; and updating the memory model, the target task model, and the N support task models based on the first loss and the respective second losses of the N support task models.

Abstract: A nanoscale positioning apparatus with a large stroke and multiple degrees of freedom and a control method thereof are provided. The nanoscale positioning apparatus includes a base, a plurality of parallel branch chain mechanisms and a working table. Each of the parallel branch chain mechanisms includes an electric cylinder, a micro-motion drive mechanism, a laser interferometer, a grating measuring device, a self-locking upper hinge and a self-locking lower hinge. The top of the base is connected to one end of the electric cylinder through the self-locking lower hinge. The other end of the electric cylinder is connected to one end of the micro-motion drive mechanism. The other end of the micro-motion drive mechanism is connected to the bottom of the working table through the self-locking upper hinge. The positioning apparatus has multiple degrees of freedom, and realizes multi-degree-of-freedom arbitrary position adjustment of the working table through parallel branch chain mechanisms.

Abstract: A nanoscale positioning apparatus with a large stroke and multiple degrees of freedom and a control method thereof are provided. The nanoscale positioning apparatus includes a base, a plurality of parallel branch chain mechanisms and a working table. Each of the parallel branch chain mechanisms includes an electric cylinder, a micro-motion drive mechanism, a laser interferometer, a grating measuring device, a self-locking upper hinge and a self-locking lower hinge. The top of the base is connected to one end of the electric cylinder through the self-locking lower hinge. The other end of the electric cylinder is connected to one end of the micro-motion drive mechanism. The other end of the micro-motion drive mechanism is connected to the bottom of the working table through the self-locking upper hinge. The positioning apparatus has multiple degrees of freedom, and realizes multi-degree-of-freedom arbitrary position adjustment of the working table through parallel branch chain mechanisms.

Abstract: A processing apparatus includes a collection module and a training module, the training module includes a backbone network and a region proposal network (RPN) layer, the backbone network is connected to the RPN layer, and the RPN layer includes a class activation map (CAM) unit. The collection module is configured to obtain an image, where the image includes an image with an instance-level label and an image with an image-level label. The backbone network is used to output a feature map of the image based on the image obtained by the collection module.

Abstract: Embodiments of the present invention provide a machine learning model training method, including: obtaining target task training data and N categories of support task training data; inputting the target task training data and the N categories of support task training data into a memory model to obtain target task training feature data and N categories of support task training feature data; training the target task model based on the target task training feature data and obtaining a first loss of the target task model, and separately training respectively corresponding support task models based on the N categories of support task training feature data and obtaining respective second losses of the N support task models; and updating the memory model, the target task model, and the N support task models based on the first loss and the respective second losses of the N support task models.