Paper Detail
Philip Matthias Winter, Maria Wimmer, Bernhard Schäfl, David Major, Dimitrios Lenis, Astrid Berg, Theresa Neubauer, Ariharasudhan Muthusami, Johannes Novotny, Georg Zotti, Katja Bühler
In open-world recognition, machine learning models not only make predictions on unknown structures ("generalized open-set"), but also continually learn and improve from those predictions over time. Interactive segmentation, despite its access to user feedback, has so far remained confined to the open-set setting. In this work we introduce MEOW, the first framework that turns non-interactive segmentation backbones into interactive open-world learners without updating learnable model parameters. MEOW combines parameter-free transductive reasoning with memory consolidation to accumulate knowledge and thereby improve future performance. Focusing on medical data, we show that MEOW consistently improves its own predictions on classes never seen during training, and transfers zero-shot to unfamiliar domains, including micro-CT data and other imaging modalities.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{winter2026meow,
title = {MEOW: Medical Open-World Interactive Segmentation},
author = {Philip Matthias Winter and Maria Wimmer and Bernhard Schäfl and David Major and Dimitrios Lenis and Astrid Berg and Theresa Neubauer and Ariharasudhan Muthusami and Johannes Novotny and Georg Zotti and Katja Bühler},
year = {2026},
abstract = {In open-world recognition, machine learning models not only make predictions on unknown structures ("generalized open-set"), but also continually learn and improve from those predictions over time. Interactive segmentation, despite its access to user feedback, has so far remained confined to the open-set setting. In this work we introduce MEOW, the first framework that turns non-interactive segmentation backbones into interactive open-world learners without updating learnable model parameters. M},
url = {https://arxiv.org/abs/2611.13935},
keywords = {cs.CV, stat.ML},
eprint = {2611.13935},
archiveprefix = {arXiv},
}
{}