Nicolas Audebert,[ONERA, The French Aerospace Lab] Abstract Investigate various methods to deal with semantic labeling of very high resolution multi-modal RS data - especially for semantic labelingContributions: 1. Multiscale approach…
by Dmitry Ulyanov,Andrea Vedaldi,Victor Lempitsky - CVPR 2018 Abstract Deep CNN - able to learn image priors from a large number of example imagesContribution: Structure of a generator network is…
Kolya Malkin, Caleb Robinson, Le Hou, Rachel Soobitsky, Jacob Czawlytko, Dimitris Samaras, Joel Saltz, Lucas Joppa, Nebojsa Jojic [Microsoft Research, Yale University, Georgia Institute of Technology, Stony Brook University, Chesapeake…
Qianru Sun, Yaoyao Liu, Tat-Seng Chua, Bernt Schiele [NUS, MaxPlank] [CVPR2019] Abstract Meta-learning - to address the challenges of the few shot learning settingsKey idea - force a large number…
by Rihuan Ke, Aurélie Bugeau, Nicolas Papadakis, Peter Schuetz, Carola-Bibiane Schönlieb [University of Cambridge] Abstract Paper proposes a DCNN for multiclass segmentation trainable on coarse data labels combined with a…
Abstract Thermal images are good at predicting objects/people at night, but poor performance in daylightSoA networks use fusion networks with paired thermal and RGB images.Contribution: augment thermal images with saliency…