Research map / Label-efficient and robust learning / Recognition and long-tail
Detecting and Correcting for Label Shift with Black Box Predictors
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Test the distribution of black-box predictions rather than high-dimensional inputs | BBSD · MNIST label-shift detection | test power | Helped |
| Train the black-box predictor for more epochs (ablation) | BBSD · MNIST label-shift detection | test power | Helped |
| Use BBSE-estimated label weights for importance-weighted ERM | BBSC · MNIST and CIFAR10 simulated label shift | prediction accuracy | Helped |
| Estimate label weights with BBSE rather than kernel mean matching | Label-shift weight estimation · MNIST simulated label shift | weight-estimation error | Helped |
Closest papers by meaning
- Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptation (ICML 2020 · similarity 0.89)
- Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition (ICML 2024 · similarity 0.86)
- Graph–Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometry (NeurIPS 2025 · similarity 0.86)
- Sequential Harmful Shift Detection Without Labels (NeurIPS 2024 · similarity 0.84)
- ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms (ICLR 2024 · similarity 0.83)
- LaSCal: Label-Shift Calibration without target labels (NeurIPS 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.