Recurrent Segmentation for Variable Computational Budgets

CVPR Workshops, 2018.

Cited by: 1|Bibtex|Views102
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

State-of-the-art systems for semantic image segmentation use feed-forward pipelines with fixed computational costs. Building an image segmentation system that works across a range of computational budgets is challenging and time-intensive as new architectures must be designed and trained for every computational setting. To address this pr...More

Code:

Data:

Your rating :
0

 

Tags
Comments