Efficient Likelihood Learning of a Generic CNN-CRF Model for Semantic Segmentation
CoRR, Volume abs/1511.05067, 2015.
Deep Models, such as Convolutional Neural Networks (CNNs), are omnipresent in computer vision, as well as, structured models, such as Conditional Random Fields (CRFs). Combining them brings many advantages, foremost the ability to in-cooperate prior knowledge into CNNs, e.g. by explicitly modelling the dependencies between output variab...更多
下载 PDF 全文