Techniques and systems are described to determine personalized digital image aesthetics in a digital medium environment. In one example, a personalized offset is generated to adapt a generic model for digital image aesthetics. A generic model, once trained, is used to generate training aesthetics scores from a personal training data set that corresponds to an entity, e.g., a particular user, group of users, and so on. The image aesthetics system then generates residual scores (e.g., offsets) as a difference between the training aesthetics score and the personal aesthetics score for the personal training digital images. The image aesthetics system then employs machine learning to train a personalized model to predict the residual scores as a personalized offset using the residual scores and personal training digital images.

A method and system for increasing data quality of a dataset for semi-supervised machine learning analysis. The method includes: receiving known class label information for a portion of the data in the dataset; receiving clustering parameters from a user; determining a data cleanliness factor, and where the data cleanliness factor is below a predetermined cleanliness threshold: assigning data without class label information as a data point to a cluster using the clustering parameters, each cluster having a cluster class label associated with such cluster; and determining a measure of assignment, and where the measure of assignment for each data point is below a predetermined assignment threshold, receiving a class label for such data points, otherwise, assigning the respective cluster class label to each data point with the respective measure of assignment below the predetermined assignment threshold; and otherwise, outputting the dataset with associated class labels for machine learning analysis.

A system for dynamic conditional guidance using artificial intelligence. The system includes a computing device, designed and configured to c calculate a diagnostic output using a biological extraction related to a user, and a first machine-learning process, wherein the diagnostic output identifies a prognostic label and an ameliorative label; classify, using a physiological classifier and a first classification algorithm, the diagnostic output to a physiological state for the user; generate a vector output for the physiological state for the user, using a clustering algorithm; receive a user input generated in response to the diagnostic output; update the vector output using the user input; and identify a recommendation for the user, utilizing the updated vector output.

Systems and methods for zero-shot prompt ensembling for zero-shot classification with text-image models can include utilizing a pre-trained text-image model to perform downstream tasks based on prompt-based weighting. The systems and methods may adjust for frequency-based bias and may automatically determine different prompt associations with a given downstream task. The systems and methods can aggregate weighted text embeddings and then determine a classification output based on similarity measures between an image embedding and the aggregated weighted text embeddings.

A computer-implemented method for domain adaptation of an object detection model includes obtaining a domain vector for a domain from one or more images in the domain, the domain vector representing the property of the domain. The domain vector is input into a fully connected layers in the object detection model. A domain-specific result of the object detection model is provided as output. The method can further include computing a domain tensor and inputting the domain tensor into convolutional layers in the object detection model.

A base pathway of a computerized two-pathway video action recognition model is trained using a plurality of labeled video samples. The base pathway is trained using a plurality of unlabeled video samples at a first framerate. An auxiliary pathway of the computerized two-pathway video action recognition model is trained using a plurality of the unlabeled video samples at a second framerate, the second framerate being slower than the first framerate, wherein the training of the base pathway and the training of the auxiliary pathway result in a trained computerized two-pathway video action recognition model. A candidate video is categorized using the trained computerized two-pathway video action recognition model and the categorized candidate video is stored in a computer-accessible video database system for information retrieval.

A device and a method for determining a class for at least a part of a digital image. The method includes: providing a classifier for a first class and a second class; determining a digital image including an object of the second class in at least the part of the digital image; determining the class for at least the part of the digital image with the classifier, wherein determining the digital image includes determining the object of the second class with a generative model depending on a label for the first class and/or depending on at least one pixel representing an object of the first class.

Various embodiments of the teachings herein include a method for generating training data for an object for training an artificial intelligence system using a training system. An example method includes: capturing a first image with the object from a first perspective; and capturing a second image with the object from a second perspective; displaying the first image; capturing input of an operator with respect to a position of the object in the first image; determining the object in the first image based on the input; generating a first item of object information based on the determined object; determining the object in the second image based on the determined first item of object information; generating a second item of object information based on the determined object in the second image; and generating training data for the object on the first item of object information and the second item of object information.

A computer-implemented method for the detection and recognition of objects in unlabeled image data using an automated labelling architecture. The method includes the steps of: proposing bounding-box in every image of the unlabeled image data using a task specific and/or a related task pretrained object detection model and a Bounding Box Sampler module; filtering said bounding boxes for positive object instances; assigning to said filtered bounding boxes a class label using a Few-Shot Classification module; and modifying filtered bounding boxes based on additional class wise attention output from the Few-Shot Classification module.

A learning mechanism with partially-labeled web images is provided while correcting the noise labels during the learning. Specifically, the mechanism employs a momentum prototype that represents common characteristics of a specific class. One training objective is to minimize the difference between the normalized embedding of a training image sample and the momentum prototype of the corresponding class. Meanwhile, during the training process, the momentum prototype is used to generate a pseudo label for the training image sample, which can then be used to identify and remove out of distribution (OOD) samples to correct the noisy labels from the original partially-labeled training images. The momentum prototype for each class is in turn constantly updated based on the embeddings of new training samples and their pseudo labels.