The disclosure is directed to an object detection method using a CNN model and an object detection apparatus thereof. In an aspect, the object detection method includes generating a sensor data; processing the sensor data by using a first object detection algorithm to generate a first object detection result; processing the first object detection result by using a plurality of stages of sparse update mapping algorithm to generate a plurality of stages of updated first object detection result; processing a first stage of the stages of updated first object detection result by using a plurality of stages of spatial pooling algorithm between each of stages of sparse update mapping algorithm; executing a plurality of stages of deep convolution layer algorithm to extract a plurality of feature results; and performing a detection prediction based on a last-stage feature result.

A method for evaluating system performance can include comparing a test average of instances of variables of test system variables to a baseline average of a baseline variables. Each of the instances of the variable of the test system variables may be shifted by a shift amount for a subset of the variables. A modified test data set may be generated from the shifted test data set. The modified test data set may be transformed with a sparse principal component analysis into test components. The test components may be compared to baseline components using a Hotelling T.sup.2 as a test statistic. Performance of the system may be quantified based upon the test statistic.

Various embodiments of systems and methods for cross media joint friend and item recommendations are disclosed herein.

Various embodiments of systems and methods for cross media joint friend and item recommendations are disclosed herein.

A method and an apparatus for detecting a salient object in an image includes separately performing convolution processing corresponding to at least two convolutional layers on a to-be-processed image to obtain at least two first feature maps of the to-be-processed image, performing superposition processing on at least two first feature maps included in a superposition set in at least two sets to obtain at least two second feature maps of the to-be-processed image, the at least two sets are in a one-to-one correspondence with the at least two second feature maps, and a resolution of a first feature map included in the superposition set is lower than or equal to a resolution of a second feature map corresponding to the superposition set, and splicing the at least two second feature maps to obtain a saliency map.

An object recognition method and apparatus for a deformed image are provided. The method includes: inputting an image into a preset localization network to obtain a plurality of localization parameters for the image, wherein the preset localization network comprises a preset number of convolutional layers, and wherein the plurality of localization parameters are obtained by regressing image features in a feature map that is generated from a convolution operation on the image; performing a spatial transformation on the image based on the plurality of localization parameters to obtain a corrected image; and inputting the corrected image into a preset recognition network to obtain an object classification result for the image. In the process of the neural network based object recognition, the embodiment of the present application first transforms the deformed image that has deformation, and then performs the object recognition on the transformed image.

A system, method and computer program product is provided. An input signal for classification and a set of pre-classified signals are received, each comprising a vector representation of an object having a plurality of vector elements. A sparse vector comprising a plurality of sparse vector coefficients is determined. Each sparse vector coefficient corresponds to a signal in the set of pre-classified signals and represents the likelihood of a match between the object represented in the input signal and the object represented in the corresponding signal. A largest sparse vector coefficient is compared with a predetermined threshold. If the largest sparse vector coefficient is less than the predetermined threshold, the corresponding signal is removed from the set of pre-classified signals. The determining and comparing are repeated using the input signal and the reduced set of pre-classified signals.

An aerial vehicle is navigated using hierarchical vision-aided navigation that classifies regions of acquired still image frames as featureless or feature-rich, and thereby avoids expending time and computational resources attempting to extract and match false features from the featureless regions. Pattern recognition registers an acquired image to a general area of a map database before performing feature matching to a finer map region. This hierarchical position determination is more efficient than attempting to ascertain a fine-resolution position without knowledge of coarse-resolution position. Resultant matched feature observations can be data-fused with other sensor data to correct a navigation solution based on GPS and/or IMU data.

Image data is run through a neural network, and the neural network produces a vector representation of the image data. Random sparse sampling masks are created. The vector representation of the image data is masked with each of the random sparse sampling masks, the masking generating corresponding sparsely sampled vectors. The sparsely sampled vectors are transmitted to nodes of a consensus network, wherein a sparsely sampled vector of the sparsely sampled vectors is transmitted to a node of the consensus network. Votes from the nodes of the consensus network are received. Whether a consensus is achieved in the votes is determined. Responsive to determining that the consensus is achieved, at least one of identification and verification of the image data may be provided.

Techniques are provided herein for contextual embedding of features of operational logs or network traffic for anomaly detection based on sequence prediction. In an embodiment, a computer has a predictive recurrent neural network (RNN) that detects an anomalous network flow. In an embodiment, an RNN contextually transcodes sparse feature vectors that represent log messages into dense feature vectors that may be predictive or used to generate predictive vectors. In an embodiment, graph embedding improves feature embedding of log traces. In an embodiment, a computer detects and feature-encodes independent traces from related log messages. These techniques may detect malicious activity by anomaly analysis of context-aware feature embeddings of network packet flows, log messages, and/or log traces.