Abstract: Methods and apparatus for training a neural network to detect living beings in an enclosed space are disclosed. An example method includes obtaining channel state information (CSI) data based at least in part on a sequence of signals received at one or more receivers located in the enclosed space, generating training data for the neural network based at least in part on the CSI data, training the neural network using the training data to detect living beings in the enclosed space, and processing the trained neural network for deployment.

Abstract: Methods and apparatus are disclosed for joint optimization of machine learning model architecture and quantization. An example method includes generating a first machine learning model for a resource-constrained device based on quantized outputs from each of a plurality of compute blocks. Each compute block includes a plurality of inverted residual blocks coupled in series. Determining the quantized output of each respective compute block includes performing a first convolution, based at least in part on a first quantization level, on input data to a first inverted residual block, performing a second convolution on an output of the first convolution based at least in part on the first quantization level, adding an output of the second convolution to the input data to generate a first quantized output, and providing the first quantized output to a second inverted residual block, and providing the first machine learning model to the resource-constrained device for execution.

Abstract: This disclosure provides methods, devices, and systems for object detection. The present implementations more specifically relate to techniques for improving distant object detection in memory-constrained computer vision systems. In some aspects, a computer vision system may include an ROI extraction component, a feature pyramid network (FPN) having a number (N) of pyramid levels, and N network heads associated with the N pyramid levels, respectively. The FPN extracts N feature maps from an input image, where the N feature maps are associated with the N pyramid levels, respectively, and each of the N network heads performs an object detection operation on a respective feature map of the N feature maps. The ROI extraction component selects a region of the feature map associated with the lowest pyramid level for distant object detection so that the object detection operation performed on that feature map is confined to the selected region.

Abstract: This disclosure provides methods, devices, and systems for object detection. The present implementations more specifically relate to region of interest (ROI) inferencing techniques that can be implemented using a single object detection model. In some aspects, a computer vision system maps a set of grid cells to an input image so that each grid cell includes a respective portion of the image, and where each of the grid cells is assigned a respective priority value. The system selects an ROI of the image based on the priority value assigned to each grid cell and performs, on the ROI, an inferencing operation associated with an object detection model. The system updates the priority values for one or more of the grid cells based on a result of the inferencing operation. The system then selects another ROI based on the updated priority values and perform the inferencing operation on the new ROI.