Disclosed are a method for training a Student Network and a method for recognizing an image. The method includes: acquiring first prediction feature information of a sample image on the first granularity and second prediction feature information of the sample image on the second granularity by inputting the sample image into a Student Network, and acquiring first feature information of the sample image on the first granularity and second feature information of the sample image on the second granularity by inputting the sample image into a Teacher Network, and acquiring a target Student Network.

There is provided with an information processing apparatus. An approximate discrimination unit discriminates an approximate type of an object from a first captured image obtained by capturing the object to which identification information is added. A setting unit sets, based on the approximate type of the object, an image capturing condition for capturing an image to obtain the identification information. A detail discrimination unit identifies the identification information from a second captured image obtained by capturing the object under the image capturing condition and discriminates a detailed type of the object based on a result of the identification.

An object detection method performed by an object detection apparatus, includes receiving an input image, obtaining, using an object detection model, a result of detecting a target candidate object from the input image, obtaining, using an error prediction model, a result of detecting an error object from the input image, and detecting a target object in the input image based on the result of detecting the target candidate object and the result of detecting the error object.

Example systems perform complex optimization tasks with improved efficiency via neural meta-optimization of experts. In particular, provided is a machine learning framework in which a meta-optimization neural network can learn to fuse a collection of experts to provide a predicted solution. Specifically, the meta-optimization neural network can learn to predict the output of a complex optimization process which optimizes over outputs from the collection of experts to produce an optimized output. In such fashion, the meta-optimization neural network can, after training, be used in place of the complex optimization process to produce a synthesized solution from the experts, leading to orders of magnitude faster and computationally more efficient prediction or problem solution.

Aspects include receiving a request to perform an image classification task in a target domain. The image classification task includes identifying a feature in images in the target domain. Classification information related to the feature is transferred from a source domain to the target domain. The transferring includes receiving a plurality of pairs of task-irrelevant images that each includes a task-irrelevant image in the source domain and in the target domain. The task-irrelevant image in the source domain has a fixed correspondence to the task-irrelevant image in the target domain. A target neural network is trained to perform the image classification task in the target domain. The training is based on the plurality of pairs of task-irrelevant images. The image classification task is performed in the target domain and includes applying the target neural network to an image in the target domain and outputting an identified feature.

A vehicle includes receiving signals from a plurality of satellites; obtaining position information based on the received signal; detecting a driving speed and yaw rate; obtaining dead reckoning information based on position information about a position of a vehicle recognized in a previous cycle and the received detection information; predicting the position information based on the obtained dead reckoning information; obtaining a value of Euclidean distance based on the position information about the position of the vehicle recognized in the previous cycle and the obtained position information; generating a first outlier filter based on the value of the Euclidean distance; obtaining a value of Mahalanobis distance based on the obtained position information and the predicted position information; generating a second outlier filter based on the value of the Mahalanobis distance; recognizing a current position of the vehicle by fusing information passing through the first outlier filter and information passing through the second outlier filter; and outputting information about the current position of the recognized vehicle as an image or a sound.

A system includes first and second sensors and a controller. The first sensor is of a first type and is configured to sense objects around a vehicle and to capture first data about the objects in a frame. The second sensor is of a second type and is configured to sense the objects around the vehicle and to capture second data about the objects in the frame. The controller is configured to down-sample the first and second data to generate down-sampled first and second data having a lower resolution than the first and second data. The controller is configured to identify a first set of the objects by processing the down-sampled first and second data having the lower resolution. The controller is configured to identify a second set of the objects by selectively processing the first and second data from the frame.

An image classification method is provided. The method includes: inputting a to-be-classified image into a plurality of neural network models; obtaining data output by multiple non-input layers specified by each neural network model to generate a plurality of image features corresponding to the plurality of neural network models; respectively inputting the plurality of corresponding image features into linear classifiers, each of the linear classifiers being trained by one of the plurality of neural network models for determining whether an image belongs to a preset class; obtaining, using each neural network model, a corresponding probability that the to-be-classified image comprises an object image of the preset class; and determining, according to each obtained probability, whether the to-be-classified image includes the object image of the preset class.

Computing systems may support image classification and image detection services, and these services may utilize object detection/image classification machine learning models. The described techniques provide for normalization of confidence scores corresponding to manipulated target images and for non-max suppression within the range of confidence scores for manipulated images. In one example, the techniques provide for generating different scales of a test image, and the system performs normalization of confidence scores corresponding to each scaled image and non-max suppression per scaled image These techniques may be used to provide more accurate image detection (e.g., object detection and/or image classification) and may be used with models that are not trained on modified image sets. The model may be trained on a standard (e.g. non-manipulated) image set but used with manipulated target images and the described techniques to provide accurate object detection.

The present disclosure describes human body attribute recognition methods and apparatus, electronic devices, and a storage medium. The method includes acquiring a sample image containing a plurality of to-be-detected areas being labeled with true values of human body attributes; generating, through a recognition model, a heat map of the sample image and heat maps of the to-be-detected areas to obtain a global heat map and local heat maps; fusing the global and the local heat maps to obtain a fused image, and performing human body attribute recognition on the fused image to obtain predicted values; determining a focus area of each type of human body attribute according to the global and the local heat maps; correcting the recognition model by using the focus area, the true values, and the predicted values; and performing, based on the corrected recognition model, human body attribute recognition on a to-be-recognized image.