Abstract: This disclosure relates to improved techniques for generating images from raw image sensor data captured in low-light conditions without the use of flash photography. The techniques described herein utilize a neural network architecture to transform the raw image sensor data into well-exposed images. The neural network architecture can be trained using a multi-criterion loss function that jointly models both pixel-level and feature-level properties of the images. The images output by the neural network architecture can be provided to a contrast correction module that enhances the contrast of the images.

Abstract: This disclosure relates to improved techniques for performing multi-view image clustering. The techniques described herein utilize machine learning functions to optimize the image clustering process. Multi-view features are extracted from a collection of images. A machine learning function is configured to jointly learn a fused binary representation that combines the multi-view features and one or more binary cluster structures that can be used to partition the images. A clustering function utilizes the fused binary representation and the one or more binary cluster structures to generate one or more image clusters based on the collection of images.

Abstract: This disclosure relates to improved techniques for performing computer vision functions including motion deblurring functions. The techniques described herein utilize a neural network architecture to perform these functions. The neural network architecture can include a human-aware attention model that is able to distinguish between foreground human objects and background portions of degraded images affected by motion blur. The neural network architecture further includes an encoder-decoder network that separately performs motion deblurring functions on foreground and background portions of degraded images, and reconstructs enhanced images corresponding to the degraded images.

Abstract: System and method for visual recognition are provided. Image data may be captured. First descriptive information may be received, for example from an external device. The image data may be analyzed to identify a group of items matching the first descriptive information. In case the group of items comprises at least two items, a second descriptive information matching a subset of the identified group of items may be generated, and in some cases the second descriptive information may be provided to the external device. In case the group of items is a group of a single item, an association of the first descriptive information and an identification value may be stored in memory, and in some cases a corresponding indication may be provided to the external device. In case the group of items is an empty group, a corresponding indication may be provided to the external device.

Abstract: Systems and methods for incremental annotation of datasets are provided. For example, a group of labeled examples and a group of unlabeled examples may be obtained, a first inference model may be generated using the group of labeled examples, labels may be assigned to at least part of the group of unlabeled examples using the first inference model, confidence levels may be assigned to the assigned labels, a subset of the group of unlabeled examples may be selected using the confidence levels, and in some cases a second inference model may be generated using the selected subset and/or the corresponding assigned labels.

Abstract: This disclosure relates to improved techniques for performing image segmentation functions using neural network architectures. The neural network architecture integrates an edge guidance module and object segmentation network into a single framework for detecting target objects and performing segmentation functions. The neural network architecture can be trained to generate edge-attention representations that preserve the edge information included in images. The neural network architecture can be trained to generate multi-scale feature information that preserves and enhances object-level feature information included in images. The edge-attention representations and multi-scale feature information can be fused to generate segmentation results that identify target object boundaries with increased accuracy.

Abstract: Systems and methods for controlling access to a dataset management system using quotas are provided. For example, a request to perform an action in a dataset management system may be obtained from an entity, and a quota record associated with the entity may be selected. Further, it may be determined if the entity has sufficient quota to perform the action. In some examples, when the entity has sufficient quota to perform the action, the request may be allowed. In some examples, when the entity has insufficient quota to perform the action, the request may be denied.

Abstract: This disclosure relates to improved techniques for performing computer vision functions on medical images, including object segmentation functions for identifying medical objects in the medical images and grading functions for determining severity labels for medical conditions exhibited in the medical images. The techniques described herein utilize a neural network architecture to perform these and other functions. The neural network architecture can be trained, at least in part, using semi-supervised learning techniques that enable the neural network architecture to accurately perform the object segmentation and grading functions despite limited availability of pixel-level annotation information.