Transcription of Three Ways To Improve Semantic Segmentation With Self ...
{{id}} {{{paragraph}}}
Three Ways to Improve Semantic Segmentationwith Self-Supervised Depth EstimationLukas HoyerETH DaiETH ChenETH K oringUniversity of SahaETH Van GoolETH Zurich & KU deep networks for Semantic Segmentation re-quires large amounts of labeled training data, whichpresents a major challenge in practice, as labeling seg-mentation masks is a highly labor-intensive process. Toaddress this issue, we present a framework for semi-supervised Semantic Segmentation , which is enhanced byself-supervised monocular depth estimation from unlabeledimage sequences. In particular, we propose Three key con-tributions: (1) We transfer knowledge from features learnedduring self-supervised depth estimation to Semantic seg-mentation, (2) we implement a strong data augmentationby blending images and labels using the geometry of thescene, and (3) we utilize the depth f
Lukas Hoyer ETH Zurich lhoyer@student.ethz.ch Dengxin Dai ETH Zurich dai@vision.ee.ethz.ch Yuhua Chen ETH Zurich yuhua.chen@vision.ee.ethz.ch Adrian Koring¨ University of Bonn adrian.koering@uni-bonn.de Suman Saha ETH Zurich suman.saha@vision.ee.ethz.ch Luc Van Gool ETH Zurich & KU Leuven vangool@vision.ee.ethz.ch Abstract
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}