Automated data analytics techniques for non-tabular data sets may include methods and systems for (1) automatically developing models that perform tasks in the domains of computer vision, audio processing, speech processing, text processing, or natural language processing; (2) automatically developing models that analyze heterogeneous data sets containing image data and non-image data, and/or heterogeneous data sets containing tabular data and non-tabular data; (3) determining the importance of an image feature with respect to a modeling task, (4) explaining the value of a modeling target based at least in part on an image feature, and (5) detecting drift in image data. In some cases, multi-stage models may be developed, wherein a pre-trained feature extraction model extracts low-, mid-, high-, and/or highest-level features of non-tabular data, and a data analytics models uses those features (or features derived therefrom) to perform a data analytics task.

A method of 3D object detection using an object detection neural network includes: receiving one or more monocular images; extracting 2D feature maps from each one of the one or more monocular images by passing the one or more monocular images through a 2D feature extracting part of the object detection neural network, generating an averaged 3D voxel volume based on the 2D feature maps, extracting a 2D representation of 3D feature maps from the averaged 3D voxel volume by passing the averaged 3D voxel volume through an encoder of a 3D feature extracting part of the object detection neural network, and performing 3D object detection as 2D object detection in a Bird's Eye View (BEV) plane, the 2D object detection in the BEV plane being performed by passing the 2D representation of 3D feature maps through thane outdoor object detecting part of the object detection neural network.

A method of 3D object detection using an object detection neural network includes: receiving one or more monocular images; extracting 2D feature maps from each one of the one or more monocular images by passing the one or more monocular images through a 2D feature extracting part of the object detection neural network, generating an averaged 3D voxel volume based on the 2D feature maps, extracting a 2D representation of 3D feature maps from the averaged 3D voxel volume by passing the averaged 3D voxel volume through an encoder of a 3D feature extracting part of the object detection neural network, and performing 3D object detection as 2D object detection in a Bird's Eye View (BEV) plane, the 2D object detection in the BEV plane being performed by passing the 2D representation of 3D feature maps through thane outdoor object detecting part of the object detection neural network.

A method of training an image classifier. The image classifier determines a prediction vector of class probabilities for an input image. First, one or more initial training steps are performed, resulting in current values for the trainable parameters of the image classifier. A training image and corresponding class label are selected, and a current label vector is determined for training the image classifier on the training image. To this end, the image classifier is applied to the training image according to the current parameter values. If the class predicted by the image classifier is equal to the class label, the current label vector is determined as a soft label based on the prediction vector. A current training step of training the image classifier on the training image is performed using the current label vector.

A method of training an image classifier. The image classifier determines a prediction vector of class probabilities for an input image. First, one or more initial training steps are performed, resulting in current values for the trainable parameters of the image classifier. A training image and corresponding class label are selected, and a current label vector is determined for training the image classifier on the training image. To this end, the image classifier is applied to the training image according to the current parameter values. If the class predicted by the image classifier is equal to the class label, the current label vector is determined as a soft label based on the prediction vector. A current training step of training the image classifier on the training image is performed using the current label vector.

It selects learning data that is effective for learning a learning model. An identification information assignment device comprising: a processor; and memory, wherein, using the memory, the processor: acquiring a plurality of image data; selecting a part of the plurality of image data as learning data; assigning identification information to the selected image data by using a learning model which is recorded in the memory; and updating the learning model by using the selected image data to which the identification information is assigned, wherein identification information is assigned to a rest of the plurality of image data by using the updated learning model, the rest of the plurality of image data being different from the selected image data.

It selects learning data that is effective for learning a learning model. An identification information assignment device comprising: a processor; and memory, wherein, using the memory, the processor: acquiring a plurality of image data; selecting a part of the plurality of image data as learning data; assigning identification information to the selected image data by using a learning model which is recorded in the memory; and updating the learning model by using the selected image data to which the identification information is assigned, wherein identification information is assigned to a rest of the plurality of image data by using the updated learning model, the rest of the plurality of image data being different from the selected image data.

A device and a method and a non-transitory readable storage medium, for face recognition are provided, the method comprise: extracting a face sample image from a predetermined face sample library and performing feature point detection to obtain multiple face feature points; obtaining multiple mask images; selecting first to fourth face feature points from the multiple face feature points; defining a distance between the first and second face feature point as a mask image height, and defining a distance between the third and fourth face feature point as a mask image width; adjusting a size of each mask image according to the mask image height and the mask image width; fusing each adjusted mask image with the face sample image to obtain multiple face mask images to save into the predetermined face sample library; training a face recognition model based on the predetermined face sample library for face recognition.

A device and a method and a non-transitory readable storage medium, for face recognition are provided, the method comprise: extracting a face sample image from a predetermined face sample library and performing feature point detection to obtain multiple face feature points; obtaining multiple mask images; selecting first to fourth face feature points from the multiple face feature points; defining a distance between the first and second face feature point as a mask image height, and defining a distance between the third and fourth face feature point as a mask image width; adjusting a size of each mask image according to the mask image height and the mask image width; fusing each adjusted mask image with the face sample image to obtain multiple face mask images to save into the predetermined face sample library; training a face recognition model based on the predetermined face sample library for face recognition.

An image processing apparatus comprises: an image input unit configured to input an image; a detection unit configured to detect an object from the image; an accepting unit configured to accept an input of a locus to the image, a selection unit configured to select, based on a locus region decided by the locus, at least two objects included in a plurality of objects detected by the detection unit; and an integration unit configured to generate an integration region that integrates at least two regions in the image corresponding to the at least two objects selected by the selection unit and set the integration region as a region of interest in the image.