International Business Machines Corporation

Intel Corporation

Microsoft International Holdings B.v.

Mattias Marder

Sivan Harary

Amir Geva

Joseph Shtok

Charles Francis Wiecha

Leonid Karlinsky

Estelle Aflalo

Noel S Kropf

Amit Bleiweiss

Dror Porat

Eliran Zimmerman

Yaoping Ruan

Sagi Katz

Jim Alain Laredo

Milton H Hernandez

Asaf Tzadok

Udi Barzelay

Ophir Azulai

Slava Shechtman

Amnon Ribak

Eliyahu Schwartz

Nandagopal Seshagiri

Yoav Nahshon

Giora Yahav

Haggai Roitman

Oded Margalit

Ariel Farkash

Somdeb Majumdar

Peter Bak

Ron Hoory

Gal Ashour

Micha Gideon Moffie

Avi Yaeli

Shay Ben-David

Yochay Tzur

Tal Drory

Ella Barkan

Sharon Alpert

Harold Jeffrey Ship

Sivan Gleichman

Fora Gilboa-Solomon

Zvi Klier

Hanlin Tang

Santiago Miret

Avrech Ben-David

Shauharda Khadka

Zvika Klier

Methods, apparatus, systems and articles of manufacture are disclosed to map workloads. An example apparatus includes a constraint definer to define performance characteristic targets of the neural network, an action determiner to apply a first resource configuration to candidate resources corresponding to the neural network, a reward determiner to calculate a results metric based on (a) resource performance metrics and (b) the performance characteristic targets, and a layer map generator to generate a resource mapping file, the mapping file including respective resource assignments for respective corresponding layers of the neural network, the resource assignments selected based on the results metric.

Methods, systems, articles of manufacture and apparatus to map workloads

Automatic multi-objective hardware optimization for processing a deep learning network is disclosed. An example of a storage medium includes instructions for obtaining client preferences for a plurality of performance indicators for processing of a deep learning workload; generating a workload representation for the deep learning workload; providing the workload representation to machine learning processing to generate a workload executable, the workload executable including hardware mapping based on the client preferences; and applying the workload executable in processing of the deep learning workload.

Automatic multi-objective hardware optimization for processing of deep learning networks

A system and method for resolving an ambiguity between similar objects in an image is disclosed. A three dimensional representation of a room is generated, and objects in the room are identified from an image of the room are identified. A determination is made that at least two objects are visually similar, and a position of the two objects is ambiguous. At least one question based on the determined ambiguity is programmatically generated based on information known about the room, and is phrased such that the ambiguity can be resolved by an answer to the question. Based on the answer received one of the objects is selected. At least one property of the selected object is modified based upon the selection of one of the at least two objects.

Object instance ambiguity resolution

A method, an apparatus and a program for automatic generation of secondary class annotations. The method comprises obtaining a plurality of images of an environment, each of which comprising objects in the environment. Some of the objects are annotated, while other objects are not. The method comprises aligning the plurality of images to a common coordinates system and computing a plurality of weighted images by adding weights to regions in the plurality of images that are associated with annotated objects to reduce significance of such regions. The method further comprises generating, based on the plurality of weighted images, a background model of the environment by determining for each region in the common coordinates system a statistical metric representing a visual feature of a background of the environment. The background model is then utilized to identify the non-annotated objects and adding an annotation for each identified object.

Automatic generation of secondary class annotations

A method can include learning a common embedding space and a set of parameters for each one of a plurality of sets of mixture models, wherein one mixture model is associated with one class of objects within a set of object categories. The method can also include adding new mixture models to the set of mixture models to support novel categories based on a set of example embedding vectors computed for each one of the novel categories. Additionally, the method includes detecting in images a plurality of boxes with associated labels and corresponding confidence scores, wherein the boxes correspond to image regions comprising objects of both known categories and the novel categories. Furthermore, the method includes, given a query image, executing an instruction based on the common embedding space and the set of mixture models, the instruction comprising identifying objects from both categories in the query image.

Representative-based metric learning for classification and few-shot object detection

Embodiments of the present disclosure include training a model using a plurality of pairs of feature vectors related to a first class. Embodiments include providing a sample feature vector related to a second class as an input to the model. Embodiments include receiving at least one synthesized feature vector as an output from the model. Embodiments include training a classifier to recognize the second class using a training data set comprising the sample feature vector related to the second class and the at least one synthesized feature vector. Embodiments include providing a query feature vector as an input to the classifier. Embodiments include receiving output from the classifier that identifies the query feature vector as being related to the second class, wherein the output is used to perform an action.

Out-of-sample generating few-shot classification networks

Embodiments of the present invention may provide automated techniques for quickly and easily installing a different model for image recognition on each of numerous devices without doing manual configuration of each and every device. For example, in an embodiment, a computer-implemented method for configuring devices may comprise capturing data at a device, transmitting the captured data to a remote system, receiving configuration data for the device, wherein the configuration data has been generated by processing the captured data at the remote system using a plurality of different machine learning techniques and generating the configuration data based on at least one of the plurality of different machine learning techniques, and configuring the device using the received configuration data.

Object detection on local devices using remotely generated machine learning models

Embodiments of the present invention may provide automated techniques for checking store shelves for compliance with planograms that can handle unknown arrangements in a uniform way, with little user involvement, and with relatively low processing complexity. For example, a computer-implemented method for determining compliance with a planogram may comprise receiving at least one image of a plurality of shelves containing objects, receiving at least one planogram representing desired positions of the objects on the shelves, wherein each row of the planogram corresponds to one shelf, adjusting positions of objects in the planogram to reflect a size of the shelves, determining a tolerance for inaccuracy in object position in the image using object dimension data, detecting object positions in the image, aligning each row of the planogram individually to the detected object positions, and comparing the detected object positions with the adjusted planogram positions to generate compliance information.

Store planogram to image registrations

There is provided a method of identifying objects in an image, comprising: extracting query descriptors from the image, comparing each query descriptor with training descriptors for identifying matching training descriptors, each training descriptor is associated with a reference object identifier and with relative location data (distance and direction from a center point of a reference object indicated by the reference object identifier), computing object-regions of the digital image by clustering the query descriptors having common center points defined by the matching training descriptors, each object-region approximately bounding one target object and associated with a center point and a scale relative to a reference object size, wherein the object-regions are computed independently of the identifier of the reference object associated with the object-regions, wherein members of each cluster point toward a common center point, and classifying the target object of each object-region according to the reference object identifier of the cluster.

Systems and methods for identifying a target object in an image

A computer-implemented method, computerized apparatus and computer program product for detecting an object's pose using a depth image. An image of an object in a scene and depth data of the scene are obtained. At least one pose hypothesis, representing a hypothesized plane, are determined based on the image. An incidence plane, hypothesized to be coplanar with the object, is determined based on the depth data. A relation indicating a level of consistency is determined between the hypothesized plane and the incidence plane for the at least one pose hypothesis.

Pose detection using depth camera

A computer-implemented method, computerized apparatus and computer program product. The method comprises capturing one or more images of a scene in which a driver is driving a vehicle; analyzing the images to retrieve an event or detail; conveying to the driver the a question or a challenge related to the event or detail; receiving a response from the driver; analyzing the response; and determining a score related to the driver.

Vehicle entertainment system

A cognitive system and method for visual classification of similar planar objects is disclosed. The method uses a query image and a list of candidate templates as the input, and produces the most probable candidate for the query image. The system uses the mutual saliency among a sample of points in the query templates, and selects those points with the highest saliency. The corresponding candidate templates to the points with the highest saliency are then compared to the query image, and those with the highest similarity are kept. The system has applications to industrial and commercial settings where processes require object recognition from image data.

Cognitive method for visual classification of very similar planar objects

Growing community of inventors

Haifa, Israel

Mattias Marder