Lightweight Model Uncertainty Estimation for Deep Neural Object Detection

Quantifying model uncertainty of Deep Neural Network (DNN) is important to understand the reliability of the model prediction and avoid risks in safety critical applications. Various approaches, including Bayesian neural networks, Monte-Carlo dropout, and ensembles, are suggested to measure the model uncertainty; but with huge computational cost. We present ModelNet, an Artificial Neural Network (ANN) that can estimate spatial/semantic model uncertainties of a DNN based object detection with less computation overhead. ModelNet is a deterministic ANN that distills the predictive distribution of stochastic DNN. Experimental results show that ModelNet can learn the uncertainty estimation from stochastic DNN in various architectures. ModelNet can perform as a probabilistic object detector with 39x-179x less number of operations, or as an uncertainty assistant to a task network with 1.4x more parameters and 38x less number of operations compared to stochastic DNN. Moreover, a case study of uncertainty driven adaptive sensor using ModelNet is presented.