Cracking open the DNN black-box
John Emmons, Sadjad Fouladi, Ganesh Ananthanarayanan, Shivaram Venkataraman, Silvio Savarese, Keith Winstein · 2019
Advancements in deep neural networks (DNNs) and widespread deployment of video cameras have fueled the need for video analytics systems. Despite rapid advances in system design, existing systems treat DNNs largely as "black boxes'' and either deploy models entirely on a camera or compress videos for analysis in the cloud. Both these approaches affect the accuracy and total cost of deployment. In this position paper, we propose a research agenda that involves opening up the black box of neural networks and describe new application scenarios that include joint inference between the cameras and the cloud, and continuous online learning for large deployments of cameras. We present promising results from preliminary work in efficiently encoding the intermediate activations sent between layers of a neural network and describe opportunities for further research.