analiza aiqbench
This research addresses the critical domain gap between synthetic cryo-ET data and real-world subtomograms, proposing a novel adaptation framework to enhance few-shot classification performance. By bridging discrepancies at both input and feature levels, the method offers a significant advancement for applying machine learning models in low-data scientific imaging scenarios.
Bridging the Synthetic-to-Real Gap for Few-Shot Cryo-ET Classification
arXiv:2609.14097v1 Announce Type: cross Abstract: Subtomogram classification in cryo-electron tomography (cryo-ET) is a challenging problem due to the scarcity of labeled examples. While cryo-ET simulators can be adopted to generate unlimited synthetic data, the substantial domain gap between synthetic and real subtomograms hinders its practical utilization. In this work, we propose a novel synthetic-to-real adaptation framework with a learnable transformation module, bridging this gap at both the input and feature levels. Extensive experiments demonstrate that our method consistently outperforms existing transfer learning baselines in few-shot settings.
Abstract:Subtomogram classification in cryo-electron tomography (cryo-ET) is a challenging problem due to the scarcity of labeled examples. While cryo-ET simulators can be adopted to generate unlimited synthetic data, the substantial domain gap between synthetic and real subtomograms hinders its practical utilization. In this work, we propose a novel synthetic-to-real adaptation framework with a learnable transformation module, bridging this gap at both the input and feature levels. Extensive experiments demonstrate that our method consistently outperforms existing transfer learning baselines in few-shot settings.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2609.14097 [cs.CV]
(or arXiv:2609.14097v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.14097 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 181 cuvinte
Subiecte conexe
[AINews] not much happened today
Latent Space · 3 oct. 2026
Do You Even Need More Data? Rethinking LLM Deployment for Label-Scarce Tabular Classification with TabLens
arXiv · 14 oct. 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · 4 sept. 2026
[AINews] Opus 5.5 is good at explainer videos
Latent Space · 29 sept. 2026