A system and method of multi-stage training of a transformer-based machine-learning model. The system performs at least two stages of the following three stages of training: During a first stage, the system pre-trains a transformer encoder via a first machine-learning network using an unlabeled 3D image dataset. During a second stage, the system fine-tunes the pre-trained transformer encoder via a second machine-learning network via a labeled 2D image dataset. During a third stage, the system further fine-tunes the previously pre-trained transformer encoder or fine-tuned transformer encoder via a third machine-learning network using a labeled 3D image dataset.

Techniques for anomaly detection are described. An exemplary method includes receiving one or more requests to train an anomaly detection machine learning model using feedback-based training, the request to indicate one or more of a type of analysis to perform, a model selection indication, and a configuration for a training dataset; training the anomaly detection machine learning model according to the one or more requests using the training data; performing feedback-based training on the trained anomaly detection machine learning model; and using the retrained anomaly detection machine learning model.

A machine-learning classification system includes a first machine-learning classifier that classifies each element of a plurality of data items to generate a plurality of classified data items. A second machine-learning classifier identifies misclassified elements of the plurality of classified data items and reclassifies each of the identified misclassified elements to generate a plurality of reclassified data items. A second machine-learning classifier identifies unclassified elements of the plurality of classified data items and classifies each of the identified unclassified elements to generate a plurality of reclassified data items. An ensemble classifier adjusts the classifications of the elements of the plurality of classified data items in response to the plurality of reclassified data items and the plurality of newly-classified elements.

Systems and methods may be used for preconditioning a model, such as for face recognition. The preconditioning may include obtaining a set of facial images, generating, from a plurality of facial images of the set, a plurality of sets of cropped images, each cropped image in the plurality of sets of cropped images including a portion of a face of an image representing a respective set, and preconditioning a machine learning model using the plurality of sets of cropped images. The machine learning model may be refined, such as using a labeled set of captured images of real faces, in an example.

Described is a system for adapting a deep convolutional neural network (CNN). A deep CNN is first trained on an annotated source image domain. The deep CNN is adapted to a new target image domain without requiring new annotations by determining domain agnostic features that map from the annotated source image domain and a target image domain to a joint latent space, and using the domain agnostic features to map the joint latent space to annotations for the target image domain.

A system for simplified generation of systems for analysis of satellite images to geolocate one or more objects of interest. A plurality of training images labeled for a study object or objects with irrelevant features loaded into a preexisting feature identification subsystem causes automated generation of models for the study object. This model is used to parameterize pre-engineered machine learning elements that are running a preprogrammed machine learning protocol. Training images with the study are used to train object recognition filters. This filter is used to identify the study object in unanalyzed images. The system reports results in a requestor's preferred format.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a variational auto-encoder (VAE) to generate disentangled latent factors on unlabeled training images. In one aspect, a method includes receiving the plurality of unlabeled training images, and, for each unlabeled training image, processing the unlabeled training image using the VAE to determine the latent representation of the unlabeled training image and to generate a reconstruction of the unlabeled training image in accordance with current values of the parameters of the VAE, and adjusting current values of the parameters of the VAE by optimizing a loss function that depends on a quality of the reconstruction and also on a degree of independence between the latent factors in the latent representation of the unlabeled training image.

A recording medium storing a program for causing a computer to execute processing including: acquiring, from a first model trained based on training data in which the first object is labeled in an image, a first portion specifying a region in an image that includes a first object; generating a third model by combining the first portion and a third portion of a second model being a model that includes a second portion and the third portion and that is trained based on training data in which position information regarding the second object is labeled in an image, the second portion being a portion that specifies a region in an image including a second object, the third portion being a portion that determines a position in an image of a specified region; and outputting a detection result of an object by inputting an image to the third model.

A few-shot object detection method includes: sending a weight of a backbone network and a weight of a feature pyramid to a detection network; generating candidate regions, in which the candidate regions derived from a result of foreground-and-background classification and regression of output features of the visual representation backbone network by a region proposal network; generating candidate region features of a uniform size using a pooling operator based on the candidate regions, and performing location regression, content classification and fine-grained feature mining on the candidate region features of the uniform size; establishing fine-grained positive sample pairs and negative sample pairs through the fine-grained feature mining, and performing comparative learning between fine-grained features of the candidate regions; and generating a loss function according to a strategy in fine-grained feature mining, and updating detection network parameters by calculating based on the loss function.

Mechanisms are provided to implement a machine learning training model. The machine learning training model trains an image generator of a generative adversarial network (GAN) to generate medical images approximating actual medical images. The machine learning training model augments a set of training medical images to include one or more generated medical images generated by the image generator of the GAN. The machine learning training model trains a machine learning model based on the augmented set of training medical images to identify anomalies in medical images. The trained machine learning model is applied to new medical image inputs to classify the medical images as having an anomaly or not.