Efficient scene parsing by sampling unary potentials in a fully-connected CRF

Abstract

Efficient, fully-connected CRF inference enables fast semantic labelling of images. However, this requires high-quality unary potentials to be computed, which is currently time-consuming. While some recent work attempts to address this issue by only computing a subset of unary potentials, a need remains for a simple, fast way to decide which unary potentials should be computed, without sacrificing accuracy. In particular, for embedded applications, a method which avoids time or memory-intensive operations is desired. In this paper, we introduce an approach to selecting good locations to compute unary potentials. We implement an efficient morphological approach to select a small proportion of pixel locations where unary potentials will be calculated. The speed of our labelling method allows us to directly search a large parameter space to optimize our method for a given task. We show that our method can achieve comparable accuracy to what can be achieved when all unary potentials are calculated, with significant time saving. Furthermore, we show that it is possible to tune our method to yield improved accuracy for certain classes of interest. We demonstrate this over multiple datasets representing challenging applications for our approach.