Abstract: Example apparatus disclosed herein are to process a first image of a first video segment from the image capture sensor with a machine learning algorithm to determine a first score for the first image, the machine learning algorithm to detect actions associated with images, the actions associated with labels. Disclosed example apparatus are also to determine a second score for the first video segment based on respective first scores for corresponding images in the first video segment. Disclosed example apparatus are further to determine, based on the second score, whether to retain the first video segment in the memory.

Abstract: Methods and apparatus are disclosed herein for computation and compression efficiency in distributed video analytics. Example apparatus disclosed herein are to identify a key frame and a non-key frame in a video frame sequence input to a neural network at a client server, determine motion information between the key frame and the non-key frame based on optical flow, and determine a frame feature representation based on the motion information reconstructed at an edge server, the motion information including feature warping residual errors.

Abstract: Embodiments of the present disclosure are directed toward probabilistic in-memory computing configurations and arrangements, and configurations of probabilistic bit devices (p-bits) for probabilistic in-memory computing. concept with emerging. A probabilistic in-memory computing device includes an array of p-bits, where each p-bit is disposed at or near horizontal and vertical wires. Each p-bit is a time-varying resistor that has a time-varying resistance, which follows a desired probability distribution. The time-varying resistance of each p-bit represents a weight in a weight matrix of a stochastic neural network. During operation, an input voltage is applied to the horizontal wires to control the current through each p-bit. The currents are accumulated in the vertical wires thereby performing respective multiply-and-accumulative (MAC) operations. Other embodiments may be described and/or claimed.

Abstract: Example apparatus disclosed herein are to process a first image of a first video segment from the image capture sensor with a machine learning algorithm to determine a first score for the first image, the machine learning algorithm to detect actions associated with images, the actions associated with labels. Disclosed example apparatus are also to determine a second score for the first video segment based on respective first scores for corresponding images in the first video segment. Disclosed example apparatus are further to determine, based on the second score, whether to retain the first video segment in the memory.

Abstract: In one embodiment, an apparatus comprises a memory and a processor. The memory is to store visual data associated with a visual representation captured by one or more sensors. The processor is to: obtain the visual data associated with the visual representation captured by the one or more sensors, wherein the visual data comprises uncompressed visual data or compressed visual data; process the visual data using a convolutional neural network (CNN), wherein the CNN comprises a plurality of layers, wherein the plurality of layers comprises a plurality of filters, and wherein the plurality of filters comprises one or more pixel-domain filters to perform processing associated with uncompressed data and one or more compressed-domain filters to perform processing associated with compressed data; and classify the visual data based on an output of the CNN.

Abstract: Features extracted from one or more layers of a trained deep neural network (DNN) are used to detect out-of-distribution (OOD) data, such as anomalies. An OOD detection process includes transforming a feature output from a layer of the DNN from a relatively high-dimensional feature space to a lower-dimensional space, and then performing a reverse transformation back to the higher-dimensional feature space, resulting in a reconstructed feature. A feature reconstruction error is calculated based on a difference between the reconstructed feature and the original feature output from the DNN. The OOD detection process may further include calculating a score based on the feature reconstruction error and generating a visual representation of the feature reconstruction error.

Abstract: In one embodiment, an apparatus comprises a memory and a processor. The memory is to store visual data associated with a visual representation captured by one or more sensors. The processor is to: obtain the visual data associated with the visual representation captured by the one or more sensors, wherein the visual data comprises uncompressed visual data or compressed visual data; process the visual data using a convolutional neural network (CNN), wherein the CNN comprises a plurality of layers, wherein the plurality of layers comprises a plurality of filters, and wherein the plurality of filters comprises one or more pixel-domain filters to perform processing associated with uncompressed data and one or more compressed-domain filters to perform processing associated with compressed data; and classify the visual data based on an output of the CNN.

Abstract: In one embodiment, an apparatus comprises a communication interface and a processor. The communication interface is to communicate with a plurality of devices. The processor is to: receive compressed data from a first device, wherein the compressed data is associated with visual data captured by sensor(s); perform a current stage of processing on the compressed data using a current CNN, wherein the current stage of processing corresponds to one of a plurality of processing stages associated with the visual data, and wherein the current CNN corresponds to one of a plurality of CNNs associated with the plurality of processing stages; obtain an output associated with the current stage of processing; determine, based on the output, whether processing associated with the visual data is complete; if the processing is complete, output a result associated with the visual data; if the processing is incomplete, transmit the compressed data to a second device.

Abstract: Disclosed is an example solution to perform source-free active adaptation to distributional shifts for machine learning. The example solution includes: interface circuitry; programmable circuitry; and instructions to cause the programmable circuitry to: perform a first training of a neural network on a baseline data set associated with a first data distribution; compare data of a shifted data set to a threshold uncertainty value, wherein the threshold uncertainty value is associated with a distributional shift between the baseline data set and the shifted data set; generate a shifted data subset including items of the shifted dataset that satisfy the threshold uncertainty value; and perform a second training of the neural network based on the shifted data subset.

Abstract: Vehicle navigation control systems in autonomous driving rely on accurate predictions of objects within the vicinity of the vehicle to appropriately control the vehicle safely through its surrounding environment. Accordingly this disclosure provides methods and devices which implement mechanisms for obtaining contextual variables of the vehicle's environment for use in determining the accuracy of predictions of objects within the vehicle's environment.

Abstract: In one embodiment, an apparatus comprises processing circuitry to: receive, via a communication interface, a compressed video stream captured by a camera, wherein the compressed video stream comprises: a first compressed frame; and a second compressed frame, wherein the second compressed frame is compressed based at least in part on the first compressed frame, and wherein the second compressed frame comprises a plurality of motion vectors; decompress the first compressed frame into a first decompressed frame; perform pixel-domain object detection to detect an object at a first position in the first decompressed frame; and perform compressed-domain object detection to detect the object at a second position in the second compressed frame, wherein the object is detected at the second position in the second compressed frame based on: the first position of the object in the first decompressed frame; and the plurality of motion vectors from the second compressed frame.

Abstract: In one embodiment, an apparatus comprises a memory and a processor. The memory is to store visual data associated with a visual representation captured by one or more sensors. The processor is to: obtain the visual data associated with the visual representation captured by the one or more sensors, wherein the visual data comprises uncompressed visual data or compressed visual data; process the visual data using a convolutional neural network (CNN), wherein the CNN comprises a plurality of layers, wherein the plurality of layers comprises a plurality of filters, and wherein the plurality of filters comprises one or more pixel-domain filters to perform processing associated with uncompressed data and one or more compressed-domain filters to perform processing associated with compressed data; and classify the visual data based on an output of the CNN.

Abstract: In one embodiment, an apparatus comprises a storage device and a processor. The storage device may store a plurality of compressed images comprising one or more compressed master images and one or more compressed slave images.

Abstract: In one embodiment, an apparatus comprises a communication interface and a processor. The communication interface is to communicate with a plurality of devices. The processor is to: receive compressed data from a first device, wherein the compressed data is associated with visual data captured by sensor(s); perform a current stage of processing on the compressed data using a current CNN, wherein the current stage of processing corresponds to one of a plurality of processing stages associated with the visual data, and wherein the current CNN corresponds to one of a plurality of CNNs associated with the plurality of processing stages; obtain an output associated with the current stage of processing; determine, based on the output, whether processing associated with the visual data is complete; if the processing is complete, output a result associated with the visual data; if the processing is incomplete, transmit the compressed data to a second device.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed that calibrate error aligned uncertainty for regression and continuous structured prediction tasks/optimizations. An example apparatus includes a prediction model, at least one memory, instructions, and processor circuitry to at least one of execute or instantiate the instructions to calculate a count of samples corresponding to an accuracy-certainty classification category, calculate a trainable uncertainty calibration loss value based on the calculated count, calculate a final differentiable loss value based on the trainable uncertainty calibration loss value, and calibrate the prediction model with the final differentiable loss value.

Abstract: Various systems and methods for providing variable bitrate compression for split deep neural network (DNN) computing are described herein. A system may be configured to manage a split DNN, the split DNN configured to operate on a compute system and a second system over a communication network. The system may access a performance metric; determine, based on the performance metric, a split point of the split DNN, the split point defining a head portion of the split DNN and a tail portion of the split DNN; determine, based on the performance metric, a bottleneck layer configuration for a bottleneck layer at the split point, the bottleneck layer including a bottleneck encoder and a bottleneck decoder; execute the head portion of the DNN and the bottleneck encoder on the compute system; and recurrently access an updated performance metric and determine a revised split point or a revised bottleneck layer configuration based on the updated performance metric.

Abstract: An apparatus comprising a memory to store an observed trajectory of a pedestrian, the observed trajectory comprising a plurality of observed locations of the pedestrian over a first plurality of timesteps; and a processor to generate a predicted trajectory of the pedestrian, the predicted trajectory comprising a plurality of predicted locations of the pedestrian over the first plurality of timesteps and over a second plurality of timesteps occurring after the first plurality of timesteps; determine a likelihood of the predicted trajectory based on a comparison of the plurality of predicted locations of the pedestrian over the first plurality of timesteps and the plurality of observed locations of the pedestrian over the first plurality of timesteps; and responsive to the determined likelihood of the predicted trajectory, provide information associated with the predicted trajectory to a vehicle to warn the vehicle of a potential collision with the pedestrian.

Abstract: Methods, apparatus, systems and articles of manufacture to improve efficiency of object tracking in video frames are disclosed. An example apparatus includes a clusterer to cluster a map of a video frame into blobs; a comparator to determine an intersection over union value between the blobs and bounding boxes in a second video frame; and an interface to initiate object detection by a neural network on the first video frame when the intersection over union does not satisfy a threshold.

Abstract: Various systems and methods for implementing distribution of a neural network workload are described herein. A discovery message is encoded that includes a latency requirement and requested resources for a workload of a neural network. A discovery response, from a proximate resource and in response to the discovery message, is decoded and includes available resources of the proximate resource available for the workload based on the requested resources for the workload. The proximate resource is selected to execute the workload based on the available resources of the proximate resource. In response to the discovery response, an offload request is encoded that includes a description of the workload. The description of the workload identifies the node to execute at the proximate resource. In response to the offload request, an input is provided to a ADAS system based on the result.

Abstract: In one embodiment, an apparatus comprises processing circuitry to: receive, via a communication interface, a compressed video stream captured by a camera, wherein the compressed video stream comprises: a first compressed frame; and a second compressed frame, wherein the second compressed frame is compressed based at least in part on the first compressed frame, and wherein the second compressed frame comprises a plurality of motion vectors; decompress the first compressed frame into a first decompressed frame; perform pixel-domain object detection to detect an object at a first position in the first decompressed frame; and perform compressed-domain object detection to detect the object at a second position in the second compressed frame, wherein the object is detected at the second position in the second compressed frame based on: the first position of the object in the first decompressed frame; and the plurality of motion vectors from the second compressed frame.