Abstract: Computer vision systems and methods for machine learning using image hallucinations are provided. The system generates image hallucinations that are subsequently used to train a deep neural network to match image patches. In this scenario, the synthesized changes serve in the learning of feature-embedding that captures how a patch of an image might look like from a different vantage point. In addition, a curricular learning framework is provided which is used to automatically train the neural network to progressively learn more invariant representations.

Abstract: Machine learning systems and methods for evaluating sampling bias in deep active classification are provided. The system generates an acquisition function based on an uncertainty based query strategy. The system utilizes the Least Confidence and the Entropy uncertainty based query strategies. The system acquires at least one data sample from the input data based on the acquisition function. The input data can include, but is not limited to, large datasets widely utilized for text classification. The system labels the data sample via an oracle and generates a training dataset with the labeled data sample. The system generates a sequence of training datasets by sampling b queries from the input data, each of size K. The system evaluates an efficiency and bias of sample datasets obtained by different query strategies. The system also trains a network with the generated training dataset(s).

Abstract: Computer vision systems and methods for localizing image forgery are provided. The system generates a constrained convolution via a plurality of learned rich filters. The system trains a convolutional neural network with the constrained convolution and a plurality of images of a dataset to learn a low level representation of each image among the plurality of images. The low level representation is indicative of a statistical signature of at least one source camera model of each image. The system can determine a splicing manipulation localization by the trained convolutional neural network.

Abstract: A system for improved localization of image forgery. The system generates a variational information bottleneck objective function and works with input image patches to implement an encoder-decoder architecture. The encoder-decoder architecture controls an information flow between the input image patches and a representation layer. The system utilizes information bottleneck to learn useful residual noise patterns and ignore semantic content present in each input image patch. The system trains a neural network to learn a representation indicative of a statistical fingerprint of a source camera model from each input image patch while excluding semantic content thereof. The system can determine a splicing manipulation localization by the trained neural network.

Abstract: A system for generating a permutation invariant representation of a graph is provided. The system assembles a dataset including a graph having a plurality of nodes and a number of features per node and generates a first matrix and a second matrix based on the plurality of nodes and the number of features per node. The system determines a set of node embeddings by a graph convolutional network based on the first matrix and the second matrix and determines a permutation invariant representation of the graph by a permutation invariant mapping based on the set of node embeddings. The system determines a universal attribute of the graph by a fully connected network based on the permutation invariant representation of the graph.

Abstract: Computer vision systems and methods for optimized computer vision using deep neural networks and Lipschitz analysis are provided. The system receives signals or data related to visual imagery, such as data from a camera, and feed-forwards the signals/data through the multiple layers of a convolutional neural network (CNN). At one or more layers of the CNN, the system determines at least one Bessel bound of that layer. The system then determines a Lipschitz bound based on the one or more Bessel bounds. The system then applies the Lipschitz bound to the signals. Once the Lipschitz bound is applied, the system can feed-forward the signals to other processes of the layer or to a further layer.

Abstract: Computer vision systems and methods for machine learning using a set packing framework are provided. A minimum weight set packing (“MWSP”) framework is parameterized by a set of possible hypotheses, each of which is associated with a real valued cost that describes the sensibility of the belief that the members of the hypothesis correspond to a common cause. Using MWSP, the system then selects the lowest total cost set of hypotheses, such that no two selected hypotheses share a common observation. Observations that are not included in any selected hypothesis, define the set of false observations can be thought of as false observations/noise. The system can be utilized to support one or more trained computer models in performing computer vision on input data in order to generate output data.

Abstract: Systems and methods for generating simulated scenes from open map data for machine learning are presented. The system includes an automatic scene generative pipeline that uses freely-available map information and random texture maps to create large-scale 3D urban scene layouts for supervised learning methods. The system generates synthetic datasets that have improved generalization capabilities with respect to a given target domain of interest using data from open maps and texture map from the same geographic locations. Data from the generation pipeline of the system improves a model's generalization to real image sets beyond arbitrarily-simulated sets or labeled real data from other geographical regions.

Abstract: Systems and methods for automatic speech recognition by training a neural network to learn features from raw speech. The system comprises a neural network executing on a computer system and comprising a feature extractor, a label classifier, and a domain classifier. The feature extractor processes raw speech data and generates a first output data. The label classifier processes the first output data and generates a second output data. The domain classifier processes the first output data and generating a third output data. The neural network calculates first loss data based on the second output, and second loss data based on the third output. Further, the neural network is trained to minimize a cross-entropy cost of the label classifier and to maximize a cross-entropy cost of the domain classifier using the first loss data and the second loss data.

Abstract: A method receives a second data set that is different from a first data set. A total number of operations based on the second data set using an operation estimator is generated. Also, an aggregate resource cost for the total number of operations based on the second data set using a resource cost estimator is generated. The method generates a simulation driver file including a sequence of operations from the total number of operations and a resource cost for each operation in the sequence of operations from the aggregate resource cost. The method simulates the sequence of operations by performing: requesting an amount of resource used by a respective operation on the simulated distributed computing system; reserving the amount of resource when available in the simulated distributed computing system without executing the respective operation; and calculating a time period associated with a simulated execution time of the respective operation.

Abstract: Computer vision systems and methods for machine learning using image hallucinations are provided. The system generates image hallucinations that are subsequently used to train a deep neural network to match image patches. In this scenario, the synthesized changes serve in the learning of feature-embedding that captures how a patch of an image might look like from a different vantage point. In addition, a curricular learning framework is provided which is used to automatically train the neural network to progressively learn more invariant representations.

Abstract: Systems and methods for unsupervised representation learning by sorting sequences are provided. An unsupervised representation learning approach is provided which uses videos without semantic labels. The temporal coherence as a supervisory signal can be leveraged by formulating representation learning as a sequence sorting task. A plurality of temporally shuffled frames (i.e., in non-chronological order) can be used as inputs and a convolutional neural network can be trained to sort the shuffled sequences and to facilitate machine learning of features by the convolutional neural network. Features are extracted from all frame pairs and aggregated to predict the correct sequence order. As sorting shuffled image sequence requires an understanding of the statistical temporal structure of images, training with such a proxy task can allow a computer to learn rich and generalizable visual representations from digital images.

Abstract: In one embodiment, a method selects a new job to schedule for execution on a data processing system. The new job includes a. Performance information for a set of current jobs that are being executed in the data processing system is retrieved where the set of jobs are assigned to queues and currently classified with a current classification. The method analyzes the performance information to determine when one or more current jobs in the set of current jobs should be re-classified due to resource usage of a respective current job when being executed in the data processing system and re-classifies the classifications for the one or more current jobs in the queues. Then, the new job is assigned to one of the queues based on the classification of the new job and the classifications of jobs in the queues including the re-classified classifications for the one or more current jobs.

Abstract: Systems and methods for detection and localization of image and document forgery. The method can include the step of receiving a dataset having a plurality of authentic images and a plurality of manipulated images. The method can also include the step of benchmarking a plurality of image forgery algorithms using the dataset. The method can further include the step of generating a plurality of receiver operating characteristic (ROC) curves for each of the plurality of image forgery algorithms. The method also includes the step of calculating a plurality of area under curve metrics for each of the plurality of ROC curves. The method further includes the step of training a neural network for image forgery based on the plurality of area under curve metrics.

Abstract: Systems and methods for optical character resolution (OCR) at low resolutions are provided. The system receives a dataset and extracts document images from the dataset. The system then segments and extracts a plurality of text lines from the document images. The system then processes the plurality of text lines using a Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) module to perform line OCR. Finally, the system generates a plurality of text strings corresponding to the plurality of text lines.

Abstract: A method receives a second data set that is different from a first data set. A total number of operations based on the second data set using an operation estimator is generated. Also, an aggregate resource cost for the total number of operations based on the second data set using a resource cost estimator is generated. The method generates a simulation driver file including a sequence of operations from the total number of operations and a resource cost for each operation in the sequence of operations from the aggregate resource cost. The method simulates the sequence of operations by performing: requesting an amount of resource used by a respective operation on the simulated distributed computing system; reserving the amount of resource when available in the simulated distributed computing system without executing the respective operation; and calculating a time period associated with a simulated execution time of the respective operation.

Abstract: In one embodiment, a method selects a new job to schedule for execution on a data processing system. The new job includes a. Performance information for a set of current jobs that are being executed in the data processing system is retrieved where the set of jobs are assigned to queues and currently classified with a current classification. The method analyzes the performance information to determine when one or more current jobs in the set of current jobs should be re-classified due to resource usage of a respective current job when being executed in the data processing system and re-classifies the classifications for the one or more current jobs in the queues. Then, the new job is assigned to one of the queues based on the classification of the new job and the classifications of jobs in the queues including the re-classified classifications for the one or more current jobs.

Abstract: A method of identifying an optimum treatment for a patient suffering from coronary artery disease, comprising: (i) providing patient information selected from: (a) status in the patient of one or more coronary disease associated biomarkers; (b) one or more items of medical history information selected from prior condition history, intervention history and medication history; (c) one or more items of diagnostic history, if the patient has a diagnostic history; and (d) one or more items of demographic data; (ii) aggregating the patient information in: (a) a Bayesian network; (b) a machine learning and neural network; (c) a rule-based system; and (d) a regression-based system; (iii) deriving a predicted probabilistic adverse event outcome for each intervention comprising percutaneous coronary intervention by placement of a bare metal stent, or a drug-coated stent; or by coronary artery bypass grafting; and (iv) determining the intervention having the lowest predicted probabilistic adverse outcome.

Abstract: A method and system for cooperative diversity visual cognition in a wireless sensor network is disclosed. The method and system are capable of solving distributed visual cognition tasks (for example, online simultaneous reconstruction of 3D models of a large area) by using multiple video streams and exploiting cooperative diversity video sensing information while ensuring an optimal tradeoff between energy consumption and video quality of images received from said multiple video streams.

Abstract: Multiple cameras are configured for use in video analytics. A single configuration tool is provided. The interrelationships between cameras are included within the configuration. Using a combination of text entry fields, registration of the cameras on a floor or other map, and marking on images from the cameras, an efficient workflow for configuration may be provided.