AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Active Learning for Probabilistic Structured Prediction of Cuts and Matchings

Sima Behpour, Anqi Liu, Brian Ziebart

ICML 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Deep active learning · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use adversarial ARC active learning instead of ActiveRBA/ActiveMLKNNActiveARC · Mulan multi-label (8 datasets)Hamming lossImproved
use adversarial ABM instead of SSVM with Platt scalingActive ABM · MOT tracking (8 mixed datasets)Hamming lossImproved
early iterations comparison of methodsActiveARC / Active ABM · Mulan and MOTHamming lossMixed
replace mutual-information solicitation with least-confident selectionactive baselines · Mulan multi-labelHamming lossHurt
use independent logistic regression baseline instead of RBA/MLKNNlogistic regression · Mulan multi-labelHamming lossHurt
MI solicitation versus random samplingML-KNN / RBA baselines · Mulan multi-labelHamming lossImproved
inference from scratch with multiple mincuts/permutations versus single mincutActive ABM/ARC · Inference timerunning time: 6-20 times slowerHurt
cache previous equilibria strategies during trainingActive ABM/ARC · Training timerunning timeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy