Example: bachelor of science
Search results with tag "Deep convolu tional neural"
and Super-Resolution arXiv:1603.08155v1 [cs.CV] 27 Mar 2016
arxiv.orgforward image transformation tasks have been solved by training deep convolu-tional neural networks with per-pixel loss functions. Semantic segmentation methods [3,5,12,13,14,15] produce dense scene labels by running a network in a fully-convolutional manner over an input image, train-ing with a per-pixel classi cation loss.