Embodiments of the present disclosure include a computer-implemented method, a system, and a computer program product for integrating bottom-up segmentation techniques into a semi-supervised image segmentation machine learning model. The computer implemented method includes training a machine learning model with a labeled dataset. The labeled dataset includes ground truth segmentation labels for each sample in the labeled dataset. The computer implemented method also includes generating a pseudo labeled dataset by applying an unlabeled dataset to the machine learning model using a top-down segmentation grouping rule. The computer implemented method further includes evaluating the pseudo labeled dataset using a bottom-up segmentation grouping rule to produce evaluation results, combining the pseudo labeled dataset with the second pseudo labeled dataset into a training dataset, and then retraining the machine learning model with the training dataset.

A multi-purpose appliance for archiving and distributing electronic copies of images is described. Methods and apparatus of the present invention relate to detecting duplicate images and/or similar image portions, grouping images and/or organizing images that are being stored and for searching stored images are described. Received images are segmented into portions and perceptual hash values are generated for each of the image portions. Information relating to image portions and an original input image are stored along with the original input image and generated image portions. The hash values of multiple images are compared and similar images are automatically grouped together into clusters. Images are identified for retrieval purposes using their hash values and/or the hash values of one or more images in a cluster in which an image is stored. An image or image portions is sometimes supplied as part of a search to retrieve similar or related images.

A system including one or more processors and one or more non-transitory computer- readable media storing computing instructions configured to run on the one or more processors and perform: creating an adjacency list for candidate items using a distance threshold; generating graphs of the candidate items in the adjacency list, wherein nodes of the graphs represent the candidate items, and wherein edges of the graphs represent respective predicted variant neighbor links between pairs of the candidate items; determining, using breakdown logic, first graphs of the graphs that exceed a predetermined size; performing divisive hierarchical clustering on each of the first graphs; and identifying recommended variant groups of the candidate item in the nested subclusters of the hierarchy dendrogram below the respective cut-off value. Other embodiments are described.

A method may include clustering form elements into line objects and columns of a table of a structured representation by applying a trained multi-dimensional clustering model to spatial coordinates of the form elements, and assigning a table header line type to a table header line object of the line objects based on a spatial coordinate of the table header line object relative to a spatial coordinate of a topmost table data line object of the line objects, and a determination that a number of columns of the table header line object is within a threshold of a number of columns of the topmost table data line object. The topmost table data line object may be assigned a table data line type. The method may further include presenting the structured representation to a user.

A system comprises an interface configured to receive an identifier, a processor configured to determine a grouping associated with the identifier, wherein the grouping is determined using a first clustering, wherein the first clustering is based at least in part on a language processing system, determine a sub-grouping of the grouping associated with the identifier, wherein the sub-grouping is determined using a second clustering, determine a final identifier based at least in part on the identifier and the sub-grouping, determine a resource based at least in part on the final identifier, and store the final identifier associated with the resource, and a memory coupled to the processor and configured to provide the processor with instructions.

According to one embodiment, a defect classification apparatus includes a processor. The processor acquires a first design image which is an image based on design data created by design software and relates to a first inspection target, and acquires a first real image which is captured by imaging the first inspection target produced based on the design data. The processor converts the first design image to a reference image represented by using a second real image captured by imaging a second inspection target without a defect. The processor calculates a reliability of the reference image. The processor detects a defect in the first inspection target by comparing the reference image and the first real image and classifies the defect, based on the reliability.

Systems, methods, tangible non-transitory computer-readable media, and devices for autonomous vehicle operation are provided. For example, a computing system can receive object data that includes portions of sensor data. The computing system can determine, in a first stage of a multiple stage classification using hardware components, one or more first stage characteristics of the portions of sensor data based on a first machine-learned model. In a second stage of the multiple stage classification, the computing system can determine second stage characteristics of the portions of sensor data based on a second machine-learned model. The computing system can generate an object output based on the first stage characteristics and the second stage characteristics. The object output can include indications associated with detection of objects in the portions of sensor data.

Aspects of the present disclosure include methods, systems, and non-transitory computer readable media that perform the steps of receiving a first plurality of snapshots, generating a first plurality of descriptors each associated with the first plurality of snapshots, grouping the first plurality of snapshots into at least one cluster based on the plurality of descriptors, selecting a representative snapshot for each of the at least one cluster, generating at least one second descriptor for the representative snapshot for each of the at least one cluster, wherein the at least one second descriptor is more complex than the first plurality of descriptors, and identifying a target by applying the at least second descriptor to a second plurality of snapshots.

An embodiment includes determining an experiential state of a first user participating in a mixed-reality experience. The embodiment also includes creating a first driver model that maps a relationship between the experiential state of the first user and a parameter of the mixed-reality experience. The embodiment also includes aggregating the first driver model with a plurality of driver models associated with experiential states and parameters of respective other users. The embodiment also includes creating a first cohort experience model using the aggregated driver models. The embodiment also includes deriving a first cohort experience parameter for the first cohort experience model. The embodiment also includes initiating an automated remedial action for participants in the mixed-reality system being associated with the first cohort experience model and the first cohort experience parameter.

A multilevel clustered data set for multidimensional vectors is created by defining a plurality of clusters based on each of the signed dimensions of the vectors, each dimension functioning as an axis. Vectors are assigned to each cluster by measuring cosine similarity between a vector and each axis. Sub-clusters are defined as ranges of cosine similarity values within a cluster, and each vector is assigned into the appropriate range based on their cosine similarity value with the axis of the cluster. Searching for a matching vector to a new vector is efficiently achieved in near-constant time by measuring cosine similarity for the new vector with each axis to identify the closest cluster, reusing the cosine similarity of the new vector and axis to determine which sub-cluster corresponds to the appropriate range of values, and then comparing each vector within the sub-cluster until a match is found or ruled out.