Lucid Data Dreaming for Video Object Segmentation

28 Mar 2017Anna KhorevaRodrigo BenensonEddy IlgThomas BroxBernt Schiele

Convolutional networks reach top quality in pixel-level video object segmentation but require a large amount of training data (1k~100k) to deliver such results. We propose a new training strategy which achieves state-of-the-art results across three evaluation datasets while using 20x~1000x less annotated data than competing methods... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.