Candidate Constrained CRFs for Loss-Aware Structured Prediction

12/10/2014 ∙ by Faruk Ahmed, et al. ∙ 0

When evaluating computer vision systems, we are often concerned with performance on a task-specific evaluation measure such as the Intersection-Over-Union score used in the PASCAL VOC image segmentation challenge. Ideally, our systems would be tuned specifically to these evaluation measures. However, despite much work on loss-aware structured prediction, top performing systems do not use these techniques. In this work, we seek to address this problem, incorporating loss-aware prediction in a manner that is amenable to the approaches taken by top performing systems. Our main idea is to simultaneously leverage two systems: a highly tuned pipeline system as is found on top of leaderboards, and a traditional CRF. We show how to combine high quality candidate solutions from the pipeline with the probabilistic approach of the CRF that is amenable to loss-aware prediction. The result is that we can use loss-aware prediction methodology to improve performance of the highly tuned pipeline system.



There are no comments yet.


page 2

page 9

page 15

page 16

page 17

page 18

page 19

page 20

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.