A system for identifying autonomous vehicles includes at least one sensor that may be configured to provide sensor data associated with at least two vehicles. A pre-processing module may be coupled to the at least one sensor and may be configured to determine a set of data including at least car following data based on the sensor data. An autonomous vehicle (AV)/human-driven vehicle (HV) identification neural network may be coupled to the pre-processing module and configured to generate an AV/HV identifier for at least one of the at least two vehicles based on at least the car following data during a predetermined time period.

The present disclosure describes techniques of improving video matting. The techniques comprise extracting features from each frame of a video by an encoder of a model, wherein the video comprises a plurality of frames; incorporating, by a decoder of the model, into any particular frame temporal information extracted from one or more frames previous to the particular frame, wherein the particular frame and the one or more previous frames are among the plurality of frames of the video, and the decoder is a recurrent decoder; and generating a representation of a foreground object included in the particular frame by the model, wherein the model is trained using segmentation dataset and matting dataset.

The present invention relates to a deep learning-based multiple skin lesion detection system, a multiple lesion detection method, and a computer-readable recording medium that has a program for implementing same recorded thereon. The system according to the present invention enables accurate classification and detection of various skin lesions having similar characteristics, on the basis of a context-dependent decision-making structure in which the local spatial correlation between various skin lesions in skin is considered.

A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

In one embodiment, a method for extracting point cloud features for use in localizing an autonomous driving vehicle (ADV) includes selecting a first set of keypoints from an online point cloud, the online point cloud generated by a LiDAR device on the ADV for a predicted pose of the ADV; and extracting a first set of feature descriptors from the first set of keypoints using a feature learning neural network running on the ADV, The method further includes locating a second set of keypoints on a pre-built point cloud map, each keypoint of the second set of keypoints corresponding to a keypoint of the first set of keypoint; extracting a second set of feature descriptors from the pre-built point cloud map; and estimating a position and orientation of the ADV based on the first set of feature descriptors, the second set of feature descriptors, and a predicted pose of the ADV.

An example apparatus for semantic image segmentation includes a receiver to receive an image to be segmented. The apparatus also includes a gated dense pyramid network including a plurality of gated dense pyramid (GDP) blocks to be trained to generate semantic labels for respective pixels in the received image. The apparatus further includes a generator to generate a segmented image based on the generated semantic labels.

A client device configured with a neural network includes a processor, a memory, a user interface, a communications interface, a power supply and an input device, wherein the memory includes a trained neural network received from a server system that has trained and configured the neural network for the client device. A server system and a method of training a neural network are disclosed.

A data processing method for a convolutional neural network includes: (a) obtaining a matrix parameter of an eigenmatrix; (b) reading corresponding data in an image data matrix from a first buffer space based on the matrix parameter through a first bus, to obtain a next to-be-expanded data matrix, and sending and storing the to-be-expanded data matrix to a second preset buffer space through a second bus; (c) reading the to-be-expanded data matrix, and performing data expansion on the to-be-expanded data matrix to obtain expanded data; (d) reading a preset number of pieces of unexpanded data in the image data matrix, sending and storing the unexpanded data to the second preset buffer space, and updating, based on the unexpanded data, the to-be-expanded data matrix; and (e). repeating (c) and (d) until all data in the image data matrix is completely read out on the to-be-expanded data matrix.

Intelligent multi-scale image parsing determines the optimal size of each observation by an artificial agent at a given point in time while searching for the anatomical landmark. The artificial agent begins searching image data with a coarse field-of-view and iteratively decreases the field-of-view to locate the anatomical landmark. After searching at a coarse field-of view, the artificial agent increases resolution to a finer field-of-view to analyze context and appearance factors to converge on the anatomical landmark. The artificial agent determines applicable context and appearance factors at each effective scale.

Techniques for increasing robustness of a convolutional neural network based on training that uses multiple datasets and multiple tasks are described. For example, a computer system trains the convolutional neural network across multiple datasets and multiple tasks. The convolutional neural network is configured for learning features from images and accordingly generating feature vectors. By using multiple datasets and multiple tasks, the robustness of the convolutional neural network is increased. A feature vector of an image is used to apply an image-related operation to the image. For example, the image is classified, indexed, or objects in the image are tagged based on the feature vector. Because the robustness is increased, the accuracy of the generating feature vectors is also increased. Hence, the overall quality of an image service is enhanced, where the image service relies on the image-related operation.