Abstract: Deep learning is used to train a neural network for end-to-end prediction of short term (e.g., 20 minutes or less) solar irradiation based on camera images and metadata. The architecture of the neural network includes a recurrent network for temporal considerations. The images and metadata are input at different locations in the neural network. The resulting machine-learned neural network predicts solar irradiation based on camera images and metadata so that a solar plant and back-up power source may be controlled to minimize output power variation.

Abstract: Systems, methods, and computer-readable media are described for determining the orientation of a target object in an image and iteratively reorienting the target object until an orientation of the target object is within an acceptable threshold of a target orientation. Also described herein are systems, methods, and computer-readable media for verifying that an image contains a target object.

Abstract: Systems, tools and methods are provided for optimizing neural networks (NNs) to run efficiently on target hardware such as central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), etc. The provided software tools are implemented as part of a machine-learning operations (MLOps) workflow for building a neural network, and include optimization algorithms (e.g., for quantization and/or pruning) and compiler processes that reduce memory requirements and processing latency.

Abstract: Systems, methods, and computer-readable media are described for performing weakly supervised semantic segmentation of input images that utilizes self-guidance on attention maps during training to cause a guided attention inference network (GAIN) to focus attention on an object in an input image in a holistic manner rather than only on the most discriminative parts of the image. The self-guidance is provided jointly by a classification loss function and an attention mining loss function. Extra supervision can also be provided by using a select number pixel-level labeled input images to enhance the semantic segmentation capabilities of the GAIN.

Abstract: A method for enhancing facial/object recognition includes receiving a query image, and providing a database of object images, including images relevant to the query image, each image having a first attribute and a second attribute with each of the first attribute and the second attribute having a first state and a second state. The method also includes creating an augmented database by generating a plurality of artificial images for each image in the database, the artificial images cooperating with the image to define a set of images including every combination of the first attribute and the second attribute in each of the first state and the second state, and comparing the query image to the images in the augmented database to find one or more matches.

Abstract: Aspects include receiving a request to perform an image classification task in a target domain. The image classification task includes identifying a feature in images in the target domain. Classification information related to the feature is transferred from a source domain to the target domain. The transferring includes receiving a plurality of pairs of task-irrelevant images that each includes a task-irrelevant image in the source domain and in the target domain. The task-irrelevant image in the source domain has a fixed correspondence to the task-irrelevant image in the target domain. A target neural network is trained to perform the image classification task in the target domain. The training is based on the plurality of pairs of task-irrelevant images. The image classification task is performed in the target domain and includes applying the target neural network to an image in the target domain and outputting an identified feature.

Abstract: A method of expanding a visual learning database in a computer by teaching the computer includes providing a series of training images to the computer wherein each series includes three images with each image falling within a unique image domain and with each image domain representing a possible combination of a first attribute and a second attribute with a first image domain including the first attribute and the second attribute in a first state (X=0, Y=0), a second image domain including the first attribute in a second state and the second attribute in the first state (X=1, Y=0), and a third image domain including the first attribute in the first state and the second attribute in the second state (X=0, Y=1).

Abstract: Systems and methods are provided for adapting images from different cameras so that a single trained classifier or an analyzer may be used. The classifier or analyzer operates on images that include a particular color distribution or characteristic. A generative network is used to adapt images from other cameras to have a similar color distribution or characteristic for use by the classifier or analyzer. A generative adversarial process is used to train the generative network.

Abstract: A system and method for visual anomaly localization in a test image includes generating, in plurality of scaled iterations, attention maps for a test image using a trained classifier network, using image-level. A current attention map is generated using an inversion of the classifier network on a condition that a forward pass of the test image in the classifier network detects a first class. One or more attention regions of the current attention map may be extracted and resized as a sub-image. For each scaled iteration, extraction of one or more regions of a current attention map is performed on a condition that the current attention map is significantly different than the preceding attention map. Visual localization of a region for the class in the test image is based on one or more of the attention maps.

Abstract: A method of expanding a visual learning database in a computer by teaching the computer includes providing a series of training images to the computer wherein each series includes three images with each image falling within a unique image domain and with each image domain representing a possible combination of a first attribute and a second attribute with a first image domain including the first attribute and the second attribute in a first state (X=0, Y=0), a second image domain including the first attribute in a second state and the second attribute in the first state (X=1, Y=0), and a third image domain including the first attribute in the first state and the second attribute in the second state (X=0, Y=1).

Abstract: Systems, methods, and computer-readable media are described for determining the orientation of a target object in an image and iteratively reorienting the target object until an orientation of the target object is within an acceptable threshold of a target orientation. Also described herein are systems, methods, and computer-readable media for verifying that an image contains a target object.

Abstract: The present embodiments relate to automatically estimating a three-dimensional pose of an object from an image captured using a camera with a structured light sensor. By way of introduction, the present embodiments described below include apparatuses and methods for training a system for and estimating a pose of an object from a test image. Training and test images are sampled to generate local image patches. Features are extracted from the local image patches to generate feature databased used to estimate nearest neighbor poses for each local image patch. The closest nearest neighbor pose to the test image is selected as the estimated three-dimensional pose.

Abstract: Systems, methods, and computer-readable media are described for training a neural network to perform keypoint detection and view-invariant keypoint representation generation. A locally learned database of three-dimensional (3D) keypoint landmarks extracted from a sample set of training depth images can be populated with view-invariant keypoint representations of the keypoint landmarks stored in association with corresponding 3D locations of the keypoint landmarks. The populated 3D keypoint landmark database can be used to find 3D keypoints that match 2D keypoints extracted from a test depth image having an unknown pose. A parameter estimation algorithm can be executed on the 3D locations of the matching keypoint landmarks to determine a pose corresponding to the test depth image.

Abstract: Deep learning is used to train a neural network for end-to-end prediction of short term (e.g., 20 minutes or less) solar irradiation based on camera images and metadata. The architecture of the neural network includes a recurrent network for temporal considerations. The images and metadata are input at different locations in the neural network. The resulting machine-learned neural network predicts solar irradiation based on camera images and metadata so that a solar plant and back-up power source may be controlled to minimize output power variation.

Abstract: A system and method for semi-supervised learning of visual recognition networks includes generating an initial set of feature representation training data based on simulated 2D test images of various viewpoints with respect to a target 3D rendering. A feature representation network generates feature representation vectors based on processing of the initial feature representation training data. Keypoint patches are labeled according to a score value based on a series of reference patches of unique viewpoint poses and a test keypoint patch processed through the trained feature representation network. A keypoint detector network learns keypoint detection based on processing of the keypoint detector training data.

Abstract: Systems and methods are provided for adapting images from different cameras so that a single trained classifier or an analyzer may be used. The classifier or analyzer operates on images that include a particular color distribution or characteristic. A generative network is used to adapt images from other cameras to have a similar color distribution or characteristic for use by the classifier or analyzer. A generative adversarial process is used to train the generative network.

Abstract: Systems, methods, and computer-readable media are described for performing weakly supervised semantic segmentation of input images that utilizes self-guidance on attention maps during training to cause a guided attention inference network (GAIN) to focus attention on an object in an input image in a holistic manner rather than only on the most discriminative parts of the image. The self-guidance is provided jointly by a classification loss function and an attention mining loss function. Extra supervision can also be provided by using a select number pixel-level labeled input images to enhance the semantic segmentation capabilities of the GAIN.

Abstract: A method for learning image representations comprises receiving a pair of images, generating a set of candidate patches in each image, identifying features in each patch, arranging the patches in pairs and comparing a distance between a feature in the first image to a feature in the second image. The pair of patches is labeled as positive or negative based on the comparison of the measured distance to a threshold. Images may be depth images and distance is determined by projecting the features into three-dimensional space. A system for learning representations includes a computer processor configured to receive a pair of images to a Siamese convolutional neural network to generate candidate patches in each image. A sampling layer arranges the patches in pairs and measures distances between features in the patches. Each pair is labeled as positive or negative according to the comparison of the distance to a threshold.

Abstract: A method for identifying a feature in a first image comprises establishing an initial database of image triplets, and in a pose estimation processor, training a deep learning neural network using the initial database of image triplets, calculating a pose for the first image using the deep learning neural network, comparing the calculated pose to a validation database populated with images data to identify an error case in the deep learning neural network, creating a new set of training data including a plurality of error cases identified in a plurality of input images and retraining the deep learning neural network using the new set of training data. The deep learning neural network may be iteratively retrained with a series of new training data sets. Statistical analysis is performed on a plurality of error cases to select a subset of the error cases included in the new set of training data.

Abstract: A method for enhancing facial/object recognition includes receiving a query image, and providing a database of object images, including images relevant to the query image, each image having a first attribute and a second attribute with each of the first attribute and the second attribute having a first state and a second state. The method also includes creating an augmented database by generating a plurality of artificial images for each image in the database, the artificial images cooperating with the image to define a set of images including every combination of the first attribute and the second attribute in each of the first state and the second state, and comparing the query image to the images in the augmented database to find one or more matches.