Disclosed herein are an apparatus and method for classifying clothing attributes based on deep learning. The apparatus includes memory for storing at least one program and a processor for executing the program, wherein the program includes a first classification unit for outputting a first classification result for one or more attributes of clothing worn by a person included in an input image, a mask generation unit for outputting a mask tensor in which multiple mask layers respectively corresponding to principal part regions obtained by segmenting a body of the person included in the input image are stacked, a second classification unit for outputting a second classification result for the one or more attributes of the clothing by applying the mask tensor, and a final classification unit for determining and outputting a final classification result for the input image based on the first classification result and the second classification result.

The present disclosure provides an image processing method, an image processing device, an electronic apparatus and a readable storage medium. The image processing method includes: obtaining feature map data of an input image; extracting a feature region in the feature map data in accordance with a size of a convolution kernel; performing windowing processing on the feature region; and obtaining a windowed feature map of the input image in accordance with the feature region obtained after the windowing processing.

A user recognition method that uses an iris is provided. The user recognition method includes generating a first mask for blocking a non-iris object area of an iris image, generating a converted iris image, in which the non-iris object area is blocked according to the first mask, generating a second mask for additionally blocking an inconsistent area, in which quantization results of the converted iris image are inconsistent, by adaptively transforming the first mask according to features of the converted iris image, obtaining an iris code by quantizing pixels included in the iris image, obtaining a converted iris code, in which portions corresponding to the non-iris object area and the inconsistent area are blocked, by applying the second mask to the iris code, and recognizing a user by matching a reference iris code, stored by the user in advance, to the converted iris code.

An artificial neural network circuit includes a crossbar circuit, and a processing circuit. The crossbar circuit transmits a signal between layered neurons of an artificial neural network. The crossbar circuit includes input bars, output bars arranged intersecting the input bars, and memristors. The processing circuit calculates a sum of signals flowing into each of the output bars. The processing circuit calculates, as the sum of the signals, a sum of signals flowing into a plurality of separate output bars and conductance values of the corresponding memristors are set so as to cooperate to give a desired weight to the signal to be transmitted.

The embodiments herein provide a method of obtaining a weighted combination of dynamic vision sensor (DVS) measurements and contact image sensor (CIS) measurements for determining visual inference in an electronic device, the method includes receiving, by the electronic device, a DVS image and a CIS image from the image sensor; determining, by the electronic device, a plurality of parameters associated with the DVS image and feature velocities of a plurality of CIS features present in the CIS image; determining, by the electronic device, a determined DVS feature confidence based on the plurality of parameters associated with the DVS image; determining, by the electronic device, a determined CIS feature confidence based on the feature velocities of the plurality of features present in the CIS image; and calculating, by the electronic device, a weighted visual inference based on the determined DVS feature confidence and the determined CIS feature confidence.

A method for local approximation of a predictive model may include receiving unclassified data associated with a plurality of unclassified data items. The unclassified data may be classified based on a first predictive model to generate classified data. A first data item may be selected from the classified data. A plurality of generated data items associated with the first data item may be generated using a generative model. The plurality of generated data items may be classified based on the first predictive model to generate classified generated data. A second predictive model may be trained with the classified generated data. A system and computer program product are also disclosed.

Example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to adapt a computing device to classify physical features in a deployment environment. In a particular implementation, computing resources may be selectively de-allocated from at least one of one or more elements of a computing architecture based, at least in part, on assessed impacts to the one or more elements of the computing architecture.

A data storage device and method for efficient image searching are provided. In one embodiment, a data storage device is provided comprising a memory and a controller. The controller is configured to store a plurality of images and a plurality of keys in the memory, wherein each key of the plurality of keys is generated from a respective image of the plurality of images; receive, from a host, a key generated from a target image desired by the host; and return, to the host, an image from the stored plurality of images that is associated with a key that matches the key received from the host. Other embodiments are provided.

A deep learning based compression (DLBC) system trains multiple models that, when deployed, generates a compressed binary encoding of an input image that achieves a reconstruction quality and a target compression ratio. The applied models effectively identifies structures of an input image, quantizes the input image to a target bit precision, and compresses the binary code of the input image via adaptive arithmetic coding to a target codelength. During training, the DLBC system reconstructs the input image from the compressed binary encoding and determines the loss in quality from the encoding process. Thus, the models can be continually trained to, when applied to an input image, minimize the loss in reconstruction quality that arises due to the encoding process while also achieving the target compression ratio.

An analysis method implemented by a computer includes: generating a refine image by changing an incorrect inference image such that a correct label score of inference is maximized, the incorrect inference image being an input image when an incorrect label is inferred in an image recognition process; and narrowing, based on a score of a label, a predetermined region to specify an image section that causes incorrect inference, the score of the label being inferred by inputting to an inferring process an image obtained by replacing the predetermined region in the incorrect inference image with the refine image.