Abstract: In one embodiment, a method includes a system building a first machine-learning module and one or more secondary machine-learning modules for operating with an application. The first and second modules may be configured to utilize, in operation, particular types of processing hardware, respectively. The system may receive from a client device a request to download the application, and in response send to the device the application with the first module. The system may then receive another request to download a selected one of the secondary modules, which may be selected based on a determination by the application running on the device that the associated type of processing hardware is available. In response, the system may send the selected module to the device. The application may be configured to selectively use the first module or the selected module to perform an operation.

Abstract: In one embodiment, a method includes a system building a first machine-learning module and one or more secondary machine-learning modules for operating with an application. The first and second modules may be configured to utilize, in operation, particular types of processing hardware, respectively. The system may receive from a client device a request to download the application, and in response send to the device the application with the first module. The system may then receive another request to download a selected one of the secondary modules, which may be selected based on a determination by the application running on the device that the associated type of processing hardware is available. In response, the system may send the selected module to the device. The application may be configured to selectively use the first module or the selected module to perform an operation.

Abstract: An image processing system transforms content images into the style of another reference style image. For example, the system applies a noise mask to generate noisy versions of the content images. The system then recomposes a content image in the style of a reference image by applying computer models to the noisy version of the content image, which reduces artifacts in the stylized image compared to that of a stylized image generated by applying the computer models to the original content image. When the content images are part of a video sequence, the image processing system may adjust the noise mask applied in a subsequent frame such that it tracks the movement of the client device from the current frame to the subsequent frame. This allows the system to reduce artifacts while stylizing the frames of the video in a consistent manner.

Abstract: An image processing system transforms content images into the style of another reference style image. For example, the system applies a noise mask to generate noisy versions of the content images. The system then recomposes a content image in the style of a reference image by applying computer models to the noisy version of the content image, which reduces artifacts in the stylized image compared to that of a stylized image generated by applying the computer models to the original content image. When the content images are part of a video sequence, the image processing system may adjust the noise mask applied in a subsequent frame such that it tracks the movement of the client device from the current frame to the subsequent frame. This allows the system to reduce artifacts while stylizing the frames of the video in a consistent manner.

Abstract: Systems and techniques are provided for a ranking approach to train deep neural nets for multilabel image annotation. Label scores may be received for labels determined by a neural network for training examples. Each label may be a positive label or a negative label for the training example. An error of the neural network may be determined based on a comparison, for each of the training examples, of the label scores for positive labels and negative labels for the training example and a semantic distance between each positive label and each negative label for the training example. Updated weights may be determined for the neural network based on a gradient of the determined error of the neural network. The updated weights may be applied to the neural network to train the neural network.

Abstract: Systems and methods are disclosed for image classification by receiving an overcomplete set of spatial regions, jointly optimizing the classifier and the pooling region for each pooled feature; and performing incremental feature selection and retraining using a grafting process to efficiently train the classifier.