arXiv Analytics

Sign in

arXiv:2010.07930 [cs.CV]AbstractReferencesReviewsResources

Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation

Hao Li, Chenxin Tao, Xizhou Zhu, Xiaogang Wang, Gao Huang, Jifeng Dai

Published 2020-10-15Version 1

We propose a general framework for searching surrogate losses for mainstream semantic segmentation metrics. This is in contrast to existing loss functions manually designed for individual metrics. The searched surrogate losses can generalize well to other datasets and networks. Extensive experiments on PASCAL VOC and Cityscapes demonstrate the effectiveness of our approach. Code shall be released.

Related articles: Most relevant | Search more
arXiv:2010.01912 [cs.CV] (Published 2020-10-05)
Best Buddies Registration for Point Clouds
arXiv:1803.02988 [cs.CV] (Published 2018-03-08)
Rethinking Feature Distribution for Loss Functions in Image Classification
arXiv:2009.13755 [cs.CV] (Published 2020-09-29)
Geometric Loss for Deep Multiple Sclerosis lesion Segmentation
Hang Zhang et al.