Abstract: A method for determining hard example sensor data inputs for training a task neural network is described. The task neural network is configured to receive a sensor data input and to generate a respective output for the sensor data input to perform a machine learning task. The method includes: receiving one or more sensor data inputs depicting a same scene of an environment, wherein the one or more sensor data inputs are taken during a predetermined time period; generating a plurality of predictions about a characteristic of an object of the scene; determining a level of inconsistency between the plurality of predictions; determining that the level of inconsistency exceeds a threshold level; and in response to the determining that the level of inconsistency exceeds a threshold level, determining that the one or more sensor data inputs comprise a hard example sensor data input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for analyzing image search result relevance. In one aspect, a method includes receiving result data specifying a search query and responsive image search results that reference images that are responsive to the search query. A determination is made that the search query matches an indexed query. An image relevance model is identified for the indexed query. The image relevance model can output a relevance score adjustment factor for an image search result based on image feature values of the image that is referenced by the search result. A relevance score adjustment factor is determined for each image search result using the identified image relevance model. A relevance score for each image search result is adjusted using the image's image relevance score adjustment factor. The images are ranked based on the adjusted relevance scores.

Abstract: Methods, systems and apparatus for refining image relevance models. In general, one aspect includes receiving a trained image relevance model that generates relevance measures of content feature values of images to a query, identifying a first threshold number of common content feature values for the set of training images, the common content feature values being identified as a set of content feature values that are each shared by at least a portion of the training images, identifying a subset of the set of training images having a quantity of the common content feature values greater than a second threshold number of content features values, and generating a re-trained image relevance model based on content feature values of the set of training images, wherein content feature values of the subset of training images are weighted higher than content feature values of the training images not in the subset.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a query image model. In one aspect, a method includes receiving a set of images determined to be responsive to a query and ranked according to a first order; determining a positive image signature from a first subset of images selected from images ranked highest in the first order, determining a negative image signature from a second subset of images selected from images ranked lowest in the first order, determining a query image signature for the query based on a difference of the positive image signature and the negative image signature; and applying the query image signature to each image in the set of images to rank the images according to a second order that is different from the first order.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying images responsive to a search phrase are disclosed. In one aspect, a method includes identifying a set of responsive images for a search phrase that includes two or more terms. Interaction rankings are determined for images in the set of responsive images. Two or more sub-queries are created based on the search phrase. Sub-query model rankings are determined for images in the set of responsive images. A search phrase score is determined for the image relevance model. Based on the search phrase scores for the sub-queries, one of the sub-query models is selected as a model for the search phrase.

Abstract: A method includes receiving a search query comprising one or more query terms, receiving image relevance models that each generate relevance measures of content feature values of images to a query, each image relevance model being a predictive model that has been trained based on content feature values of a set of training images, and each of the queries being a unique set of one or more query terms received by a search system as a query input, identifying an image relevance model for a different query that has been identified as similar to the received search query, and calculating a fractional adjustment multiplier for search results responsive to the received search query, the fractional adjustment multiplier being based on a relevance measure generated by the identified image relevance model for the different query and based on a degree of similarity between the different query and the received search query.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying images responsive to a search phrase are disclosed. In one aspect, a method includes identifying a set of responsive images for a search phrase that includes two or more terms. Interaction rankings are determined for images in the set of responsive images. Two or more sub-queries are created based on the search phrase. Sub-query model rankings are determined for images in the set of responsive images. A search phrase score is determined for the image relevance model. Based on the search phrase scores for the sub-queries, one of the sub-query models is selected as a model for the search phrase.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for analyzing image search result relevance. In one aspect, a method includes receiving result data specifying a search query and responsive image search results that reference images that are responsive to the search query. A determination is made that the search query matches an indexed query. An image relevance model is identified for the indexed query. The image relevance model can output a relevance score adjustment factor for an image search result based on image feature values of the image that is referenced by the search result. A relevance score adjustment factor is determined for each image search result using the identified image relevance model. A relevance score for each image search result is adjusted using the image's image relevance score adjustment factor. The images are ranked based on the adjusted relevance scores.

Abstract: A method includes receiving a search query comprising one or more query terms, receiving image relevance models that each generate relevance measures of content feature values of images to a query, each image relevance model being a predictive model that has been trained based on content feature values of a set of training images, and each of the queries being a unique set of one or more query terms received by a search system as a query input, identifying an image relevance model for a different query that has been identified as similar to the received search query, and calculating a fractional adjustment multiplier for search results responsive to the received search query, the fractional adjustment multiplier being based on a relevance measure generated by the identified image relevance model for the different query and based on a degree of similarity between the different query and the received search query.

Abstract: Methods, systems and apparatus for refining image relevance models. In general, one aspect includes receiving a trained image relevance model that generates relevance measures of content feature values of images to a query, identifying a first threshold number of common content feature values for the set of training images, the common content feature values being identified as a set of content feature values that are each shared by at least a portion of the training images, identifying a subset of the set of training images having a quantity of the common content feature values greater than a second threshold number of content features values, and generating a re-trained image relevance model based on content feature values of the set of training images, wherein content feature values of the subset of training images are weighted higher than content feature values of the training images not in the subset.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for classifying images. In one aspect, a method includes receiving training samples for a particular data dimension. Each training sample specifies a training value for the data dimension and a measure of relevance between the training sample and a phrase. A value range is determined for the data dimension. The value range is segmented into two or more segments. A predictive model is trained for each segment. The predictive model for each segment is trained to predict an output based on an input value that is within the segment. A classification sample specifying an input value is received. A classification output is computed based on the input value, the predictive model for the segment in which the input value is included, and the predictive model for an adjacent segment.

Abstract: Methods and apparatuses perform thickness compensation in anatomical images. The method according to one embodiment accesses digital image data representing an image including a breast; estimates thickness of the breast at multiple locations inside the breast using an image data characteristic and a reference tissue in the breast; compensates thickness of the breast using a thickness model; and refines compensation of breast thickness from the compensating step.

Abstract: A method and an apparatus automatically detect eyeglasses in an image. The method according to one embodiment accesses digital image data representing an image including a face; detects eyeglasses in the image by using nose ridge masking; and outputs a decision about presence or absence of eyeglasses in the image.

Abstract: A method and an apparatus automatically detect and remove eyeglasses from an image. The method according to one embodiment accesses digital image data representing an image including a face; detects eyeglasses in the image to produce a report about presence or absence of eyeglasses in the image; normalizes illumination of the image to obtain a normalized image; and removes eyeglasses from the normalized image to obtain a face image without eyeglasses.

Abstract: Methods and apparatuses align breast images. The method according to one embodiment accesses digital image data representing a first breast image including a left breast, and a second breast image including a right breast; removes from the first and second breast images artifacts not related to the left and right breasts; and aligns the left and right breasts using a similarity measure between the first and second breast images, the similarity measure depending on a relative position of the first and second breast images.

Abstract: Methods and apparatuses perform thickness compensation in anatomical images. The method according to one embodiment accesses digital image data representing an image including a breast; estimates thickness of the breast at multiple locations inside the breast using an image data characteristic and a reference tissue in the breast; compensates thickness of the breast using a thickness model; and refines compensation of breast thickness from the compensating step.

Abstract: A method and an apparatus automatically detect and remove eyeglasses from an image. The method according to one embodiment accesses digital image data representing an image including a face; detects eyeglasses in the image to produce a report about presence or absence of eyeglasses in the image; normalizes illumination of the image to obtain a normalized image; and removes eyeglasses from the normalized image to obtain a face image without eyeglasses.

Abstract: A method and an apparatus automatically detect eyeglasses in an image. The method according to one embodiment accesses digital image data representing an image including a face; detects eyeglasses in the image by using nose ridge masking; and outputs a decision about presence or absence of eyeglasses in the image.