Abstract: An information processing device comprises a setting unit configured to set, as difficult case data, training data for which an erroneous result is output by a hierarchical neural network that has performed training using a training data group, an updating unit configured to generate an updated hierarchical neural network in which a layer for detecting the difficult case data is added to the hierarchical neural network, and a training unit configured to perform training processing of the updated hierarchical neural network using the training data group.

Abstract: An information processing apparatus performs estimation processing on supervised data, and stores a relationship between teacher information and an estimation result. When unsupervised data is input, the information processing apparatus searches for supervised data high in degree of similarity in estimation result to unsupervised data, and generates teacher information from an estimation result of unsupervised data based on a relationship between teacher information and an estimation result about the detected supervised data.

Abstract: There is provided with a training apparatus for training a neural network. The neural network, when an input image is inputted, outputs a detection result of a first type and a detection result of a second type for each position of the input image. A training data obtaining unit obtains a training image to be input to the neural network for training. An error map obtaining unit obtains an error map indicating a detection error for a detection result of the first type, for each position of the training image. A training unit trains the neural network using the detection result of the first type and the detection result of the second type that are obtained by inputting the training image to the neural network, and the error map.

Abstract: An apparatus includes a learning unit configured to perform learning of a neural network, using a mini batch having a configuration pattern generated based on class information of learning data, and a determination unit configured to determine a configuration pattern to be utilized for next learning, based on a learning result obtained by the learning unit, wherein the learning unit performs next learning, using a mini batch having the determined configuration pattern.

Abstract: An information processing apparatus performs estimation processing on supervised data, and stores a relationship between teacher information and an estimation result. When unsupervised data is input, the information processing apparatus searches for supervised data high in degree of similarity in estimation result to unsupervised data, and generates teacher information from an estimation result of unsupervised data based on a relationship between teacher information and an estimation result about the detected supervised data.

Abstract: When there are a plurality of detection candidate objects, to detect a target object that is appropriately visible as a whole, an information processing apparatus calculates detection likelihoods in a plurality of local areas of each of the plurality of detection target candidates, and a detection reliability of each of the detection target candidates based on a distribution of the detection likelihoods.

Abstract: An object gripping apparatus includes an image capturing unit for capturing a region including a plurality of works, an obtaining unit for obtaining distance information of the region, a measurement unit for measuring three-dimensional positions/orientations of a plurality of gripping-candidate works out of the plurality of works based on the image and distance information, thereby generating three-dimensional position/orientation information, a selection unit for selecting a gripping-target work based on the three-dimensional position/orientation information, a gripping unit for gripping the gripping-target work, and an updating unit for updating the three-dimensional position/orientation information by measuring three-dimensional positions/orientations of the gripping-candidate works at a time interval during gripping of the gripping-target work.

Abstract: An information processing apparatus including an acquisition unit that acquires a plurality of image sets obtained by different acquisition methods, a generation unit that generates partial image sets by extracting corresponding partial images from respective images of the image sets, an assignment unit that assigns the partial image sets to a root node of a tree structure, a setting unit that sets, at each node of the tree structure, positions of a plurality of pixels for each partial image set assigned to the node, a determination unit that determines whether any one of the plurality of pixels in a. partial image obtained by a predetermined one of the different acquisition methods in each partial image set has an invalid value, and a selection unit that selects art acquisition method based on the determination.

Abstract: When there are a plurality of detection candidate objects, to detect a target object that is appropriately visible as a whole, an information processing apparatus calculates detection likelihoods in a plurality of local areas of each of the plurality of detection target candidates, and a detection reliability of each of the detection target candidates based on a distribution of the detection likelihoods.

Abstract: A classification result is stored in advance. At the time of identification, classification is performed at a high speed based on the stored classification result. In pre-classification, classification is performed divisionally in two stages. In the first classification, a plurality of representative vectors are generated from the classification result using a fast executable method. In the second classification, the created representative vectors are classified, and the result is stored in a lookup table. When an identification target image is input, the classification result can be reflected at a high speed by using the lookup table.

Abstract: One of different channels is selected using the pixel values of a plurality of pixels in partial images of a predetermined channel in a current set assigned to a currently referred node. The partial image of the selected channel is set as a target partial image. A node corresponding to the pixel values of a plurality of pixels in the target partial image is selected out of nodes under the currently referred node. The current set is assigned to the selected node. Information about the set assigned to the end node is output.

Abstract: An object gripping apparatus includes an image capturing unit for capturing a region including a plurality of works, an obtaining unit for obtaining distance information of the region, a measurement unit for measuring three-dimensional positions/orientations of a plurality of gripping-candidate works out of the plurality of works based on the image and distance information, thereby generating three-dimensional position/orientation information, a selection unit for selecting a gripping-target work based on the three-dimensional position/orientation information, a gripping unit for gripping the gripping-target work, and an updating unit for updating the three-dimensional position/orientation information by measuring three-dimensional positions/orientations of the gripping-candidate works at a time interval during gripping of the gripping-target work.

Abstract: A classification result is stored in advance. At the time of identification, classification is performed at a high speed based on the stored classification result. In pre-classification, classification is performed divisionally in two stages. In the first classification, a plurality of representative vectors are generated from the classification result using a fast executable method. In the second classification, the created representative vectors are classified, and the result is stored in a lookup table. When an identification target image is input, the classification result can be reflected at a high speed by using the lookup table.