Systems and methods for determining input data is out-of-domain of an AI (artificial intelligence) based system are provided. Input data for inputting into an AI based system is received. An in-domain feature space of the AI based system and an out-of-domain feature space of the AI based system are modelled. The in-domain feature space corresponds to features of data that the AI based system is trained to classify. The out-of-domain feature space corresponds to features of data that the AI based system is not trained to classify. Probability distribution functions in the in-domain feature space and the out-of-domain feature space are generated for the input data and for the data that the AI based system is trained to classify. It is determined whether the input data is out-of-domain of the AI based system based on the probability distribution functions for the input data and for the data that the AI based system is trained to classify.

A computer-implemented method for automatically annotating frames of sensor data includes: receiving the frames of sensor data; grouping the frames into a plurality of packets based on at least one condition attribute, wherein the at least one condition attribute describes at least one environment condition that existed while a respective frame of sensor data was being recorded; annotating frames from a first packet using a neural network, wherein the annotating comprises assigning at least one data point to each frame, wherein the first packet comprises frames for which the at least one condition attribute is in a selected value range; selecting a first sample of one or more frames from the first packet and determining a quality measure for data points of the first sample; and ascertaining that the quality measure for the first sample is below a predefined threshold.

Quality associated with an interpretation of data captured as unstructured data can be determined. Attributes can be identified within the unstructured data automatically. Subsequently, sentiment associated with each of the attributes can be determined based on the unstructured data. Correctness of the unstructured data, and thus the interpretation, can be assessed based on a comparison of the attribute and associated sentiment with structured data. A quality score can be generated that captures the quality of the data interpretation in terms of correctness and as well as results of another analysis including completeness, among others. Comparison of the quality score to a threshold can dictate whether or not the interpretation is subject to further review.

Methods, apparatus, systems, and storage medium for a face liveness detection are provided. The method includes obtaining an image comprising a face of an object; extracting an image feature of the image through an encryption network in a joint model for encryption and detection; performing image reconstruction based on the image feature to obtain an encrypted image corresponding to the image, the encrypted image being different in image content from the image; transmitting the encrypted image to a liveness detection server, wherein the liveness detection server is configured to perform liveness detection on the encrypted image through a detection network in the joint model for encryption and detection to obtain a liveness detection result of the object in the image; and receiving the liveness detection result of the object in the image from the liveness detection server.

An object detection model training apparatus, method and non-transitory computer readable storage medium thereof are provided. The apparatus performs a first object detection on a plurality of training images to generate a piece of first label information corresponding to each of the training images by a first teacher model. The apparatus trains a student model based on the training images and the first label information. The apparatus performs a second object detection on the training images to generate a piece of second label information corresponding to each of the training images by a second teacher model. The apparatus trains the student model based on the training images and the second label information.

This disclosure describes an automated process for training an ML model used by a computer vision system in a point of sale (POS) system to recognize a new item. Instead of relying on a manual process performed by a data scientist, the automated process can use images of a new (i.e., unknown) item captured at one or more POS systems to then retrain the ML model to recognize the new item. That is, the images of the item are used to retrain the ML model and to test the accuracy of the updated ML model. If the updated ML model can confidently identify the new item, the updated ML model is then used by the computer vision system to identify items at the POS system.

A system, method and apparatus to label video images with assistance from an artificial neural network. After a user provides first inputs to label first aspects of an object shown in a first video frame, the artificial neural network infers or predicts second aspects to be labeled for the object in a second video frame. A graphical user interface presents the inferred or predicted second aspects over a display of the second video frame to allow the user to confirm or modify the inference or prediction. For example, an object of interest in the first frame can be labeled with a classification and a bounding box; and the artificial neural network is trained to infer or predict, for the corresponding object in the second frame, its bounding box, classification, and pixels represented of the image of the object in the second frame.

An image processing method includes acquiring a set of image samples for training an attribute recognition model, wherein the set of image samples includes a first subset of image samples with category labels and a second subset of image samples without category labels; training a sample prediction model using the first subset of image samples, and predicting categories of the image samples in the second subset of image samples using the trained sample prediction model; determining a category distribution of the set of image samples based on the category labels of the first subset of image samples and the predicted categories of the second subset of image samples; and acquiring a new image sample if the determined category distribution does not conform to the expected category distribution, and adding the acquired new image sample to the set of image samples.

A processor derives a first feature amount for an object included in an image by a first neural network, and derives a second feature amount for a sentence including description of an object by a second neural network. The processor acquires each of a first attribute, which is an attribute of the object included in the image, and a second attribute, which is an attribute of the sentence. The processor trains the first and second neural networks such that, in a feature space to which first and second feature amounts belong, as relevance of a combination of the first and the second attributes is higher a distance between the derived first feature amount and second feature amount is smaller.

A method for remotely assessing oral health of a user of a mobile device by obtaining, using the mobile device (40), at least one digital image (1) of said user's (30) oral cavity (31) and additional non-image data (2) comprising anamnestic information about the user (30). The digital image (1) is processed both using a statistical object detection algorithm (20) to extract at least one local visual feature (3) corresponding to a medical finding related to a sub-region of said user's oral cavity (31); and also using a statistical image recognition algorithm (21) to extract at least one global classification label (4) corresponding to a medical finding related to said user's oral cavity (31) as a whole. An assessment (10) of the oral health of said user (30) is determined based on the local visual feature(s) (3), the global classification label(s) (4) and the non-image data (2).