Latent Structured Active Learning
Wenjie Luo · Alex Schwing · Raquel Urtasun

Thu Dec 5th 07:00 -- 11:59 PM @ Harrah's Special Events Center, 2nd Floor #None

In this paper we present active learning algorithms in the context of structured prediction problems. To reduce the amount of labeling necessary to learn good models, our algorithms only label subsets of the output. To this end, we query examples using entropies of local marginals, which are a good surrogate for uncertainty. We demonstrate the effectiveness of our approach in the task of 3D layout prediction from single images, and show that good models are learned when labeling only a handful of random variables. In particular, the same performance as using the full training set can be obtained while only labeling ~10\% of the random variables.

Author Information

Wenjie Luo (TTI Chicago)
Alex Schwing (University of Illinois at Urbana-Champaign)
Raquel Urtasun (University of Toronto)

More from the Same Authors