This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize image-guided model inversion of an image classifier with a discriminator. The disclosed systems utilize a neural network image classifier to encode features of an initial image and a target image. The disclosed system also reduces a feature distance between the features of the initial image and the features of the target image at a plurality of layers of the neural network image classifier by utilizing a feature distance regularizer. Additionally, the disclosed system reduces a patch difference between image patches of the initial image and image patches of the target image by utilizing a patch-based discriminator with a patch consistency regularizer. The disclosed system then generates a synthesized digital image based on the constrained feature set and constrained image patches of the initial image.

A method, apparatus and system for zero shot object detection includes, in a semantic embedding space having embedded object class labels, training the space by embedding extracted features of bounding boxes and object class labels of labeled bounding boxes of known object classes into the space, determining regions in an image having unknown object classes on which to perform object detection as proposed bounding boxes, extracting features of the proposed bounding boxes, projecting the extracted features of the proposed bounding boxes into the space, computing a similarity measure between the projected features of the proposed bounding boxes and the embedded, extracted features of the bounding boxes of the known object classes in the space, and predicting an object class label for proposed bounding boxes by determining a nearest embedded object class label to the projected features of the proposed bounding boxes in the space based on the similarity measures.

A human identifying device includes a temperature sensing module, a temperature pattern recognizing module and a human body identifying module. The temperature sensing module senses temperature distribution within the target area. The temperature pattern recognizing module determines at least one matching region out of the target area based on a human-resembling temperature feature within the temperature distribution. The temperature pattern recognizing module identifies at least one matching temperature sensor that corresponds to the at least one matching region. The human body identifying module determines if distribution of the at least one matching temperature sensor resembles at least one part of a human body contour.

An object detection system according to the present invention includes: an object presence region prediction means that predicts an object presence region, which is a region in which a target object exists in a current image, based on information indicating the target object detected in a past image; an object presence region fragment generation means that generates object presence region fragments, which are partial regions of the object presence region, based on the object presence region; an object detection means that detects an object detection fragment, which is a region containing the target object, based on the object presence region fragment; and a target object detection means that detects the target object from the current image using the object detection fragment.

Systems and methods for image segmentation are described. Embodiments of the present disclosure receive a training image and a caption for the training image, wherein the caption includes text describing an object in the training image; generate a pseudo mask for the object using a teacher network based on the text describing the object; generate a mask for the object using a student network; compute noise information for the training image using a noise estimation network; and update parameters of the student network based on the mask, the pseudo mask, and the noise information.

A system includes a memory and at least one processor to acquire a hyperspectral image of a food object by an imaging device, the hyperspectral image of the food object comprising a three-dimensional set of images of the food object, each image in the set of images representing the food object in a wavelength range of the electromagnetic spectrum, normalize the hyperspectral image of the food object, select a region of interest in the hyperspectral image, the region of interest comprising a subset of at least one image in the set of images, extract spectral features from the region of interest in the hyperspectral image, and compare the spectral features from the region of interest with a plurality of images in a training set to determine particular characteristics of the food object and determine that the hyperspectral image indicates a foreign object.

A method, apparatus and computer program product for removing weather elements, such as rain, from images are provided. In this regard, imagery from self-driving cars or video surveillance may be blurred by weather elements. The weather elements may be removed by utilizing pure weather element images. The pure weather element images may be processed by machine learning techniques to model pure weather element data, and generate a pure weather element dictionary. Imagery including both weather elements and background scenery may then be processed accordingly, and the weather elements removed based on the learned pure weather element dictionary. Resulting weather-free images may then be generated.

The information processing apparatus (2000) includes a feature point detection unit (2020), a determination unit (2040), an extraction unit (2060), and a comparison unit (2080). A feature point detection unit (2020) detects a plurality of feature points from the query image. The determination unit (2040) determines, for each feature point, one or more object images estimated to include the feature point. The extraction unit (2060) extracts an object region estimated to include the object in the query image in association with the object image of the object estimated to be included in the object region, on the basis of the result of the determination. The comparison unit (2080) cross-checks the object region with the object image associated with the object region and determines an object included in the object region.

A device include on-board memory, an applications processor, a digital signal processor (DSP) cluster, a configurable accelerator framework (CAF), and at least one communication bus architecture. The communication bus communicatively couples the applications processor, the DSP cluster, and the CAF to the on-board memory. The CAF includes a reconfigurable stream switch and data volume sculpting circuitry, which has an input and an output coupled to the reconfigurable stream switch. The data volume sculpting circuitry receives a series of frames, each frame formed as a two dimensional (2D) data structure, and determines a first dimension and a second dimension of each frame of the series of frames. Based on the first and second dimensions, the data volume sculpting circuitry determines for each frame a position and a size of a region-of-interest to be extracted from the respective frame, and extracts from each frame, data in the frame that is within the region-of-interest.

A display control unit displays a tomographic image of a specific tomographic plane in a first medical image on a display unit. A finding classification unit classifies each pixel of a partial region of the first medical image into at least one finding. A feature amount calculation unit calculates a first feature amount for each finding in the partial region. A weighting coefficient setting unit sets a weighting coefficient indicating a degree of weighting, which varies depending on a size of each finding, for each finding. A similarity derivation unit performs a weighting operation for the first feature amount for each finding calculated in the partial region and a second feature amount for each finding calculated in a second medical image on the basis of the weighting coefficient to derive a similarity between the first medical image and the second medical image.