One embodiment of the present invention sets forth a technique for performing inference operations associated with a trained machine learning model. The technique includes comparing a first input image with a plurality of image representations that are associated with a plurality of output classes predicted by the trained machine learning model. The technique also includes determining that the first input image does not match any image representation included in the plurality of image representations and subsequently determining that the first input image does match a first alternative representation that is associated with a first output class included in the plurality of output classes. The technique further includes generating a first prediction that indicates that the first input image is a member of the first output class.

One embodiment of the present invention sets forth a technique for performing inference operations associated with a trained machine learning model. The technique includes comparing a first input image with a plurality of image representations that are associated with a plurality of output classes predicted by the trained machine learning model. The technique also includes determining that the first input image does not match any image representation included in the plurality of image representations and subsequently determining that the first input image does match a first alternative representation that is associated with a first output class included in the plurality of output classes. The technique further includes generating a first prediction that indicates that the first input image is a member of the first output class.

A method for optimizing an image classification model can include determining a first image classification model based on initial training data; in response to model optimization, determining a second image classification model based on the first image classification model and a noise data set; and obtaining a third image classification model by optimizing the second image classification model based on the initial training data, the third image classification model being configured to update the noise data set based on noise data generated within a predetermined time period and the noise data set.

An information processing system (10) includes: an acquisition unit (50) configured to sequentially acquire a plurality of elements included in sequential data; a first calculation unit (110) configured to calculate, for each of the plurality of elements, a first indicator indicating which one of a plurality of classes the element belongs to; a weight calculation unit (130) configured to calculate, for each of the plurality of elements, a weight according to a confidence related to calculation of the first indicator; a second calculation unit (120) configured to calculate, based on the first indicators each weighted with the weight, a second indicator indicating which one of the plurality of classes the sequential data belongs to; and a classification unit (60) configured to classify the sequential data as any one of the plurality of classes, based on the second indicator. According to such an information processing system, sequential data can be appropriately classified.

An information processing system (10) includes: an acquisition unit (50) configured to sequentially acquire a plurality of elements included in sequential data; a first calculation unit (110) configured to calculate, for each of the plurality of elements, a first indicator indicating which one of a plurality of classes the element belongs to; a weight calculation unit (130) configured to calculate, for each of the plurality of elements, a weight according to a confidence related to calculation of the first indicator; a second calculation unit (120) configured to calculate, based on the first indicators each weighted with the weight, a second indicator indicating which one of the plurality of classes the sequential data belongs to; and a classification unit (60) configured to classify the sequential data as any one of the plurality of classes, based on the second indicator. According to such an information processing system, sequential data can be appropriately classified.

Methods, systems, articles of manufacture, and apparatus to extract shape features based on a structural angle template are disclosed. An example apparatus includes a template generator to generate a template based on an input image and calculate a template value based on values in the template; a bit slicer to calculate an OR bit slice and an AND bit slice based on the input image, combine the OR bit slice with the AND bit slice to generate a fused image, group a plurality of pixels of the fused image to generate a pixel window, each pixel of the pixel window including a pixel value, and calculate a window value based on the pixel values of the pixel window; and a comparator to compare the template value with the window value and store the pixel window in response to determining the window value satisfies a similarity threshold with the template value.

The present disclosure provides an object association method and apparatus, and an electronic device, which relate to the technical field of maps. A specific implementation solution is: when performing object association, extracting first description information of each of a plurality of first objects from real data, and extracting second description information of each of a plurality of second objects from high-definition map data; and determining, according to the first description information and the second description information, association probabilities between the first objects and the second objects; then determining, according to the association probabilities between the first objects and the second objects, an association result of the first objects and the second objects, thus realizing automatic associations between objects in real world and objects in a high-definition map, and improving an association efficiency of objects.

The present disclosure provides an object association method and apparatus, and an electronic device, which relate to the technical field of maps. A specific implementation solution is: when performing object association, extracting first description information of each of a plurality of first objects from real data, and extracting second description information of each of a plurality of second objects from high-definition map data; and determining, according to the first description information and the second description information, association probabilities between the first objects and the second objects; then determining, according to the association probabilities between the first objects and the second objects, an association result of the first objects and the second objects, thus realizing automatic associations between objects in real world and objects in a high-definition map, and improving an association efficiency of objects.

A portable terminal configured to estimate the number of used wet towels, or oshiboris, stored in a collection box, including: an information receiving unit for receives pre-collection store information; a photographing unit for capturing an image of used oshiboris stored in a collection box from above; a learning model storing unit for storing a learning model trained by a neural network; an image acquiring unit for acquiring an image for estimation photographed by the photographing unit. The estimating unit estimates a number of used oshiboris from the image for estimation acquired by the image acquiring unit, with the learning model stored in the learning model storing unit, by the neural network. The display unit displays an estimation result estimated by the estimating unit. The information transmitting unit transmits post-collection store information added the estimation result to the pre-collection store information received by the information receiving unit to the core system.

A portable terminal configured to estimate the number of used wet towels, or oshiboris, stored in a collection box, including: an information receiving unit for receives pre-collection store information; a photographing unit for capturing an image of used oshiboris stored in a collection box from above; a learning model storing unit for storing a learning model trained by a neural network; an image acquiring unit for acquiring an image for estimation photographed by the photographing unit. The estimating unit estimates a number of used oshiboris from the image for estimation acquired by the image acquiring unit, with the learning model stored in the learning model storing unit, by the neural network. The display unit displays an estimation result estimated by the estimating unit. The information transmitting unit transmits post-collection store information added the estimation result to the pre-collection store information received by the information receiving unit to the core system.