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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use adversarial ARC active learning instead of ActiveRBA/ActiveMLKNN | ActiveARC · Mulan multi-label (8 datasets) | Hamming loss | Improved |
| use adversarial ABM instead of SSVM with Platt scaling | Active ABM · MOT tracking (8 mixed datasets) | Hamming loss | Improved |
| early iterations comparison of methods | ActiveARC / Active ABM · Mulan and MOT | Hamming loss | Mixed |
| replace mutual-information solicitation with least-confident selection | active baselines · Mulan multi-label | Hamming loss | Hurt |
| use independent logistic regression baseline instead of RBA/MLKNN | logistic regression · Mulan multi-label | Hamming loss | Hurt |
| MI solicitation versus random sampling | ML-KNN / RBA baselines · Mulan multi-label | Hamming loss | Improved |
| inference from scratch with multiple mincuts/permutations versus single mincut | Active ABM/ARC · Inference time | running time: 6-20 times slower | Hurt |
| cache previous equilibria strategies during training | Active ABM/ARC · Training time | running time | Improved |
Closest papers by meaning
- Efficient and Consistent Adversarial Bipartite Matching (ICML 2018 · similarity 0.87)
- Multi-Classifier Adversarial Optimization for Active Learning (AAAI 2023 · similarity 0.86)
- Active Learning for Deep Object Detection via Probabilistic Modeling (ICCV 2021 · similarity 0.86)
- Active Domain Adaptation with False Negative Prediction for Object Detection (CVPR 2024 · similarity 0.84)
- Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees (AAAI 2024 · similarity 0.84)
- Plug and Play Active Learning for Object Detection (CVPR 2024 · similarity 0.83)
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.
