Abstract: In implementations of systems for generating images for virtual try-on and pose transfer, a computing device implements a generator system to receive input data describing a first digital image that depicts a person in a pose and a second digital image that depicts a garment. Candidate appearance flow maps are computed that warp the garment based on the pose at different pixel-block sizes using a first machine learning model. The generator system generates a warped garment image by combining the candidate appearance flow maps as an aggregate per-pixel displacement map using a convolutional gated recurrent network. A conditional segment mask is predicted that segments portions of a geometry of the person using a second machine learning model. The generator system outputs a digital image that depicts the person in the pose wearing the garment based on the warped garment image and the conditional segmentation mask using a third machine learning model.

Abstract: Techniques described herein extract form structures from a static form to facilitate making that static form reflowable. A method described herein includes accessing low-level form elements extracted from a static form. The method includes determining, using a first set of prediction models, second-level form elements based on the low-level form elements. Each second-level form element includes a respective one or more low-level form elements. The method further includes determining, using a second set of prediction models, high-level form elements based on the second-level form elements and the low-level form elements. Each high-level form element includes a respective one or more second-level form elements or low-level form elements. The method further includes generating a reflowable form based on the static form by, for each high-level form element, linking together the respective one or more second-level form elements or low-level form elements.

Abstract: Embodiments disclosed herein describe systems, methods, and products that generate trained neural networks that are robust against adversarial attacks. During a training phase, an illustrative computer may iteratively optimize a loss function that may include a penalty for ill-conditioned weight matrices in addition to a penalty for classification errors. Therefore, after the training phase, the trained neural network may include one or more well-conditioned weight matrices. The one or more well-conditioned weight matrices may minimize the effect of perturbations within an adversarial input thereby increasing the accuracy of classification of the adversarial input. By contrast, conventional training approaches may merely reduce the classification errors using backpropagation, and, as a result, any perturbation in an input is prone to generate a large effect on the output.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group).

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that recognize speech from a digital video utilizing an unsupervised machine learning model, such as a generative adversarial neural network (GAN) model. In one or more implementations, the disclosed systems utilize an image encoder to generate self-supervised deep visual speech representations from frames of an unlabeled (or unannotated) digital video. Subsequently, in one or more embodiments, the disclosed systems generate viseme sequences from the deep visual speech representations (e.g., via segmented visemic speech representations from clusters of the deep visual speech representations) utilizing the adversarially trained GAN model. Indeed, in some instances, the disclosed systems decode the viseme sequences belonging to the digital video to generate an electronic transcription and/or digital audio for the digital video.

Abstract: Systems and methods for topic modeling are described. The systems and methods include encoding words of a document using an embedding matrix to obtain word embeddings for the document. The words of the document comprise a subset of words in a vocabulary, and the embedding matrix is trained as part of a topic attention network based on a plurality of topics. The systems and methods further include encoding a topic-word distribution matrix using the embedding matrix to obtain a topic embedding matrix. The topic-word distribution matrix represents relationships between the plurality of topics and the words of the vocabulary. The systems and methods further include computing a topic context matrix based on the topic embedding matrix and the word embeddings and identifying a topic for the document based on the topic context matrix.

Abstract: Techniques described herein extract form structures from a static form to facilitate making that static form reflowable. A method described herein includes accessing low-level form elements extracted from a static form. The method includes determining, using a first set of prediction models, second-level form elements based on the low-level form elements. Each second-level form element includes a respective one or more low-level form elements. The method further includes determining, using a second set of prediction models, high-level form elements based on the second-level form elements and the low-level form elements. Each high-level form element includes a respective one or more second-level form elements or low-level form elements. The method further includes generating a reflowable form based on the static form by, for each high-level form element, linking together the respective one or more second-level form elements or low-level form elements.

Abstract: Methods and systems are provided for facilitating generation and utilization of a commonsense contextualizing machine learning (ML) model, in accordance with embodiments described herein. In embodiments, a commonsense contextual ML model is trained by fine-tuning a pre-trained language model using a set of training path-sentence pairs. Each training path-sentence pair includes a commonsense path, identified via a commonsense knowledge graph, and a natural language sentence identified as contextually related to the commonsense path. The trained commonsense contextualizing ML model can then be used to generate a commonsense inference path for a text input. Such a commonsense inference path can include a sequence of entities and relations that provide commonsense context to the text input. Thereafter, the commonsense inference path can be provided to a natural language processing system for use in performing a natural language processing task.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.

Abstract: A technique is disclosed for generating class level rules that globally explain the behavior of a machine learning model, such as a model that has been used to solve a classification problem. Each class level rule represents a logical conditional statement that, when the statement holds true for one or more instances of a particular class, predicts that the respective instances are members of the particular class. Collectively, these rules represent the pattern followed by the machine learning model. The techniques are model agnostic, and explain model behavior in a relatively easy to understand manner by outputting a set of logical rules that can be readily parsed. Although the techniques can be applied to any number of applications, in some embodiments, the techniques are suitable for interpreting models that perform the task of classification. Other machine learning model applications can equally benefit.

Abstract: Embodiments are disclosed for training a neural network classifier to learn to more closely align an input image with its attribution map. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a training image comprising a representation of one or more objects, the training image associated with at least one label for the representation of the one or more objects, generating a perturbed training image based on the training image using a neural network, and training the neural network using the perturbed training image by minimizing a combination of classification loss and attribution loss to learn to align an image with its corresponding attribution map.

Abstract: Systems, methods, and computer storage media are disclosed for predicting visual compatibility between a bundle of catalog items (e.g., a partial outfit) and a candidate catalog item to add to the bundle. Visual compatibility prediction may be jointly conditioned on item type, context, and style by determining a first compatibility score jointly conditioned on type (e.g., category) and context, determining a second compatibility score conditioned on outfit style, and combining the first and second compatibility scores into a unified visual compatibility score. A unified visual compatibility score may be determined for each of a plurality of candidate items, and the candidate item with the highest unified visual compatibility score may be selected to add to the bundle (e.g., fill the in blank for the partial outfit).

Abstract: This disclosure includes technologies for image processing, particularly for image generation and editing in a configurable semantic direction. A generative adversarial network is trained with an auxiliary network with an auxiliary task that is designed to disentangle the latent space of the generative adversarial network. Resultantly, a new type of GAN is created to improve image generation or editing in both conditional and unconditional settings.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for generating combined feature embeddings for minority class upsampling in training machine learning models with imbalanced training samples. For example, the disclosed systems can select training sample values from a set of training samples and a combination ratio value from a continuous probability distribution. Additionally, the disclosed systems can generate a combined synthetic training sample value by modifying the selected training sample values using the combination ratio value and combining the modified training sample values. Moreover, the disclosed systems can generate a combined synthetic ground truth label based on the combination ratio value. In addition, the disclosed systems can utilize the combined synthetic training sample value and the combined synthetic ground truth label to generate a combined synthetic training sample and utilize the combined synthetic training sample to train a machine learning model.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate interactive visual shape representation of digital datasets. For example, the disclosed systems can generate an augmented nearest neighbor network graph from a sampled subset of digital data points using a nearest neighbor model and witness complex model. The disclosed system can further generate a landmark network graph based on the augmented nearest neighbor network graph utilizing a plurality of random walks. The disclosed systems can also generate a loop-augmented spanning network graph based on a partition of the landmark network graph by adding community edges between communities of landmark groups based on modularity and to complete community loops. Based on the loop-augmented spanning network graph, the disclosed systems can generate an interactive visual shape representation for display on a client device.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating trained neural network with increased robustness against adversarial attacks by utilizing a dynamic dropout routine and/or a cyclic learning rate routine. For example, the disclosed systems can determine a dynamic dropout probability distribution associated with neurons of a neural network. The disclosed systems can further drop neurons from a neural network based on the dynamic dropout probability distribution to help neurons learn distinguishable features. In addition, the disclosed systems can utilize a cyclic learning rate routine to force copy weights of a copy neural network away from weights of an original neural network without decreasing prediction accuracy to ensure that the decision boundaries learned are different.

Abstract: Methods, computer systems, computer-storage media, and graphical user interfaces are provided for determining user affinities by tracking historical user interactions with tagged digital content and using the user affinities in content generation applications. Accordingly, the system may track user interactions with published digital content in order to generate user interaction reports whenever a user engages with the digital content. The system may aggregate the interaction reports to generate an affinity profile for a user or audience of users. A marketer may then generate digital content for a target user or audience of users and the system may process the digital content to generate a set of tags for the digital content. Based on the set of tags, the system may then evaluate the digital content in view of the affinity profile for the target user/audience to determine similarities or differences between the digital content and the affinity profile.

Abstract: Embodiments are disclosed for training a neural network classifier to learn to more closely align an input image with its attribution map. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a training image comprising a representation of one or more objects, the training image associated with at least one label for the representation of the one or more objects, generating a perturbed training image based on the training image using a neural network, and training the neural network using the perturbed training image by minimizing a combination of classification loss and attribution loss to learn to align an image with its corresponding attribution map.

Abstract: Techniques are described for machine learning-based generation of target segments is leveraged in a digital medium environment. A segment targeting system generates training data to train a machine learning model to predict strength of correlation between a set of users and a defined demographic. Further, a machine learning model is trained with visit statistics for the users to predict the likelihood that the users will visit a particular digital content platform. Those users with the highest predicted correlation with the defined demographic and the highest likelihood to visit the digital content platform can be selected and placed within a target segment, and digital content targeted to the defined demographic can be delivered to users in the target segment.

Abstract: Local data can be made available in a cloud computing environment. A persistent remote connection may be established between a processor and a server. The server may receive a request for data from an external device through a network. The request for data may be sent through the persistent remote connection from the server to a first executable process of the processor. The processor may obtain the data from an application being executed by the processor separately from the first executable process. The data may be sent through the persistent remote connection from the processor to the server. The server may send the data to the external device through the network in response to the request. The persistent remote connection may be maintained in an open state regardless of a status of the request for data.