Systems and methods for performing image search are described. An image search method may include generating a feature vector for each of a plurality of stored images using a machine learning model trained using a rotation loss term, receiving a search query comprising a search image with object having an orientation, generating a query feature vector for the search image using the machine learning model, wherein the query feature vector is based at least in part on the orientation, comparing the query feature vector to the feature vector for each of the plurality of stored images, and selecting at least one stored image of the plurality of stored images based on the comparison, wherein the at least one stored image comprises a similar orientation to the orientation of the object in the search image.

Interpretation maps of convolutional neural networks having certifiable robustness using Rényi differential privacy are provided. In one aspect, a method for generating an interpretation map includes: adding generalized Gaussian noise to an image x to obtain T noisy images, wherein the generalized Gaussian noise constitutes perturbations to the image x; providing the T noisy images as input to a convolutional neural network; calculating T noisy interpretations of output from the convolutional neural network corresponding to the T noisy images; re-scaling the T noisy interpretations using a scoring vector υ to obtain T re-scaled noisy interpretations; and generating the interpretation map using the T re-scaled noisy interpretations, wherein the interpretation map is robust against the perturbations.

Interpretation maps of convolutional neural networks having certifiable robustness using Rényi differential privacy are provided. In one aspect, a method for generating an interpretation map includes: adding generalized Gaussian noise to an image x to obtain T noisy images, wherein the generalized Gaussian noise constitutes perturbations to the image x; providing the T noisy images as input to a convolutional neural network; calculating T noisy interpretations of output from the convolutional neural network corresponding to the T noisy images; re-scaling the T noisy interpretations using a scoring vector υ to obtain T re-scaled noisy interpretations; and generating the interpretation map using the T re-scaled noisy interpretations, wherein the interpretation map is robust against the perturbations.

An approach for integrating logical graphics display (100) and geographic display system data (200) into building automation systems that allow users to navigate between the logical graphics displays and the geographic displays and to select the logical graphics displays and the geographic displays that are displayed on the displays to the users of the building automation systems.

A training method for a robust neural network based on feature matching is provided in this disclosure, which includes following steps. Step A, a first stage model is initialized. The first stage model includes a backbone network, a feature matching module and a fullple loss function. Step B, the first stage model is trained by using original training data to obtain a second stage model. Step C, the second stage model is attacked so as to generate PGD adversarial samples of the original training data, and the second stage model is trained again with the generated adversarial samples and the original training data. Step D, training parameters are adjusted and the second stage model is trained again, and parameters for which the model has highest accuracy on an original test set are saved.

A training method for a robust neural network based on feature matching is provided in this disclosure, which includes following steps. Step A, a first stage model is initialized. The first stage model includes a backbone network, a feature matching module and a fullple loss function. Step B, the first stage model is trained by using original training data to obtain a second stage model. Step C, the second stage model is attacked so as to generate PGD adversarial samples of the original training data, and the second stage model is trained again with the generated adversarial samples and the original training data. Step D, training parameters are adjusted and the second stage model is trained again, and parameters for which the model has highest accuracy on an original test set are saved.

An electronic apparatus is provided. The electronic apparatus includes an input interface, a memory configured to store a plurality of first embedding vectors and content information related to each of the plurality of first embedding vectors, and at least one processor. The at least one processor is configured to obtain a sketch input of a user through the input interface, obtain a second embedding vector by inputting the sketch input to a neural network model, identify a first embedding vector, among the plurality of first embedding vectors, having a highest similarity with the second embedding vector, and obtain and output content information corresponding to the identified first embedding vector.

An electronic apparatus is provided. The electronic apparatus includes an input interface, a memory configured to store a plurality of first embedding vectors and content information related to each of the plurality of first embedding vectors, and at least one processor. The at least one processor is configured to obtain a sketch input of a user through the input interface, obtain a second embedding vector by inputting the sketch input to a neural network model, identify a first embedding vector, among the plurality of first embedding vectors, having a highest similarity with the second embedding vector, and obtain and output content information corresponding to the identified first embedding vector.

A method implemented by computer for the semantic description of the content of an image comprising the steps consisting in receiving a signature associated with the image; receiving a plurality of groups of initial visual concepts; the method comprising the steps of expressing the signature of the image in the form of a vector comprising components referring to the groups of initial visual concepts; and modifying the signature by applying a filtering rule applicable to the components of the vector. Developments describe, in particular, intra-group or inter-group, thresholds-based and/or order-statistic-based filtering rules, partitioning techniques including the visual similarity of the images and/or semantic similarity of the concepts, the optional addition of manual annotations to the semantic description of the image. The advantages of the method in respect of parsimonious and diversified semantic representation are presented.

A physical object is scanned and a digital image of the object is generated from the scan. At least one subset of the image, known as an “authentication region” is selected. A plurality of feature vectors, arising from the physical structure of the object, are extracted from certain locations of interest within an authentication region and combined to generate a unique identifier or “digital fingerprint” for that object. Preferably, authentication regions for feature vector extraction are automatically selected by a software process. To identify or authenticate an object, a system may compare a digital fingerprint of an object to digital fingerprints previously stored in a database. Digital fingerprint data may specify a set of features (also termed “locations of interest”) which may be referenced in the creation of a “fingerprint template” which is a template of certain locations of interest and/or attributes selected for authenticating a particular class of objects.