Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating high-resolution images using self-attention based neural networks. One of the systems includes a neural network configured to generate images, the neural network comprising a sequence of one or more first network blocks followed by a sequence of one or more second network blocks, wherein: each first network block is configured to perform operations comprising: applying a self-attention mechanism over at least a subset of first elements of a first block input to generate an updated first block input; and upsampling the updated first block input to generate a first block output; and each second network block is configured to perform operations comprising: processing a second block input using one or more neural network layers to generate an updated second block input; and upsampling the updated second block input to generate a second block output.

Abstract: A method includes receiving a training data set including a plurality of training data subsets. From two or more training data subsets in the training data set, the method includes selecting a support set of training examples and a query set of training examples. The method includes determining, using the classification model, a centroid value for each respective class. For each training example in the query set of training examples, the method includes generating, using the classification model, a query encoding, determining a class distance measure, determining a ground-truth distance, and updating parameters of the classification model. For each training example in the query set of training examples identified as being misclassified, the method further includes generating a standard deviation value, sampling a new query, and updating parameters of the confidence model based on the new query encoding.

Abstract: A method for extracting entities comprises obtaining a document that includes a series of textual fields that includes a plurality of entities. Each entity represents information associated with a predefined category. The method includes generating, using the document, a series of tokens representing the series of textual fields. The method includes generating an entity prompt that includes the series of tokens and one of the plurality of entities and generating a schema prompt that includes a schema associated with the document. The method includes generating a model query that includes the entity prompt and the schema prompt and determining, using an entity extraction model and the model query, a location of the one of the plurality of entities among the series of tokens. The method includes extracting, from the document, the one of the plurality of entities using the location of the one of the plurality of entities.

Abstract: A method for training a model comprises obtaining a set of labeled training samples each associated with a given label. For each labeled training sample, the method includes generating a pseudo label and estimating a weight of the labeled training sample indicative of an accuracy of the given label. The method also includes determining whether the weight of the labeled training sample satisfies a weight threshold. When the weight of the labeled training sample satisfies the weight threshold, the method includes adding the labeled training sample to a set of cleanly labeled training samples. Otherwise, the method includes adding the labeled training sample to a set of mislabeled training samples. The method includes training the model with the set of cleanly labeled training samples using corresponding given labels and the set of mislabeled training samples using corresponding pseudo labels.

Abstract: A method includes obtaining a set of unlabeled training samples. For each training sample in the set of unlabeled training samples generating, the method includes using a machine learning model and the training sample, a corresponding first prediction, generating, using the machine learning model and a modified unlabeled training sample, a second prediction, the modified unlabeled training sample based on the training sample, and determining a difference between the first prediction and the second prediction. The method includes selecting, based on the differences, a subset of the set of unlabeled training samples. For each training sample in the subset of the set of unlabeled training samples, the method includes obtaining a ground truth label for the training sample, and generating a corresponding labeled training sample based on the training sample paired with the ground truth label. The method includes training the machine learning model using the corresponding labeled training samples.

Abstract: A method for rehearsal-free continual learning includes obtaining a set of training samples where training sample in the set of training samples is associated with a respective task of a plurality of different tasks. The method includes obtaining a task-invariant prompt representative of learned knowledge common to each respective task of the plurality of different tasks. The method includes, for each respective task of the plurality of different tasks, obtaining a respective task-specific prompt representative of learned knowledge specific to the respective task. The method includes, during each of one or more training iterations, for each respective training sample in the set of training samples, selecting the respective task-specific prompt representative of the respective task of the respective training sample and training a model using the task-invariant prompt and the selected respective task-specific prompt.

Abstract: A method includes receiving a training data set including a plurality of training data subsets. From two or more training data subsets in the training data set, the method includes selecting a support set of training examples and a query set of training examples. The method includes determining, using the classification model, a centroid value for each respective class. For each training example in the query set of training examples, the method includes generating, using the classification model, a query encoding, determining a class distance measure, determining a ground-truth distance, and updating parameters of the classification model. For each training example in the query set of training examples identified as being misclassified, the method further includes generating a standard deviation value, sampling a new query, and updating parameters of the confidence model based on the new query encoding.

Abstract: A method includes receiving image data including a series of image patches of an image. The method includes generating, using a first set of transformers of a vision transformer (V-T) model, a first set of higher order feature representations based on the series of image patches and aggregating the first set of higher order feature representations into a second set of higher order feature representations that is smaller than the first set. The method includes generating, using a second set of transformers of the V-T model, a third set of higher order feature representations based on the second set of higher order feature representations and aggregating the third set of higher order feature representations into a fourth set of higher order feature representations that is smaller than the third set. The method includes generating, using the V-T model, an image classification of the image based on the fourth set.

Abstract: A method for jointly training a classification model and a confidence model. The method includes receiving a training data set including a plurality of training data subsets. From two or more training data subsets in the training data set, the method includes selecting a support set of training examples and a query set of training examples. The method includes determining, using the classification model, a centroid value for each respective class. For each training example in the query set of training examples, the method includes generating, using the classification model, a query encoding, determining a class distance measure, determining a ground-truth distance, and updating parameters of the classification model. For each training example in the query set of training examples identified as being misclassified, the method further includes generating a standard deviation value, sampling a new query, and updating parameters of the confidence model based on the new query encoding.

Abstract: A method for jointly training a classification model and a confidence model. The method includes receiving a training data set including a plurality of training data subsets. From two or more training data subsets in the training data set, the method includes selecting a support set of training examples and a query set of training examples. The method includes determining, using the classification model, a centroid value for each respective class. For each training example in the query set of training examples, the method includes generating, using the classification model, a query encoding, determining a class distance measure, determining a ground-truth distance, and updating parameters of the classification model. For each training example in the query set of training examples identified as being misclassified, the method further includes generating a standard deviation value, sampling a new query, and updating parameters of the confidence model based on the new query encoding.

Abstract: Systems and methods for generating synthesized images are provided. An input medical image of a patient in a first domain is received. A synthesized image in a second domain is generated from the input medical image of the patient in the first domain using a first generator. The first generator is trained based on a comparison between segmentation results of a training image in the first domain from a first segmentor and segmentation results of a synthesized training image in the second domain from a second segmentor. The synthesized training image in the second domain is generated by the first generator from the training image in the first domain. The synthesized image in the second domain is output.

Abstract: A method for training a model comprises obtaining a set of labeled training samples each associated with a given label. For each labeled training sample, the method includes generating a pseudo label and estimating a weight of the labeled training sample indicative of an accuracy of the given label. The method also includes determining whether the weight of the labeled training sample satisfies a weight threshold. When the weight of the labeled training sample satisfies the weight threshold, the method includes adding the labeled training sample to a set of cleanly labeled training samples. Otherwise, the method includes adding the labeled training sample to a set of mislabeled training samples. The method includes training the model with the set of cleanly labeled training samples using corresponding given labels and the set of mislabeled training samples using corresponding pseudo labels.

Abstract: A method for active learning includes obtaining a set of unlabeled training samples and for each unlabeled training sample, perturbing the unlabeled training sample to generate an augmented training sample. The method includes generating, using a machine learning model, a predicted label for both samples and determining an inconsistency value for the unlabeled training sample that represents variance between the predicted labels for the unlabeled and augmented training samples. The method includes sorting the unlabeled training samples based on the inconsistency values and obtaining, for a threshold number of samples selected from the sorted unlabeled training samples, a ground truth label. The method includes selecting a current set of labeled training samples including each selected unlabeled training samples paired with the corresponding ground truth label. The method includes training, using the current set and a proper subset of unlabeled training samples, the machine learning model.

Abstract: Systems and methods for generating synthesized images are provided. An input medical image of a patient in a first domain is received. A synthesized image in a second domain is generated from the input medical image of the patient in the first domain using a first generator. The first generator is trained based on a comparison between segmentation results of a training image in the first domain from a first segmentor and segmentation results of a synthesized training image in the second domain from a second segmentor. The synthesized training image in the second domain is generated by the first generator from the training image in the first domain. The synthesized image in the second domain is output.