18334840. SYSTEMS AND METHODS FOR REDUCING POWER CONSUMPTION OF EXECUTING LEARNING MODELS IN VEHICLE SYSTEMS (Verizon Patent and Licensing Inc.)
Contents
SYSTEMS AND METHODS FOR REDUCING POWER CONSUMPTION OF EXECUTING LEARNING MODELS IN VEHICLE SYSTEMS
Organization Name
Verizon Patent and Licensing Inc.
Inventor(s)
Tomaso Trinci of Florence (IT)
Tommaso Bianconcini of Florence (IT)
Leonardo Taccari of Florence (IT)
Leonardo Sarti of Florence (IT)
Francesco Sambo of Florence (IT)
SYSTEMS AND METHODS FOR REDUCING POWER CONSUMPTION OF EXECUTING LEARNING MODELS IN VEHICLE SYSTEMS
This abstract first appeared for US patent application 18334840 titled 'SYSTEMS AND METHODS FOR REDUCING POWER CONSUMPTION OF EXECUTING LEARNING MODELS IN VEHICLE SYSTEMS
Original Abstract Submitted
A device may receive video data that includes a plurality of video frames, and may utilize a scheduling policy to divide the plurality of video frames into a first set of video frames and a second set of video frames. The device may process the first set of video frames, with a first convolutional neural network (CNN) model that includes one or more saliency gates, to generate first predictions and saliency maps, and may generate a trained first CNN model based on the first predictions and the saliency maps. The device may process the second set of video frames and the saliency maps, with a second CNN model that includes a saliency propagation module, to generate second predictions, and may generate a trained second CNN model based on the second predictions. The device may perform actions based on the trained first CNN model and the trained second CNN model.
