Fully Unsupervised Probabilistic Noise2Void

التفاصيل البيبلوغرافية
العنوان: Fully Unsupervised Probabilistic Noise2Void
المؤلفون: Alexander Krul, Manan Lalit, Florian Jug, Mangal Prakash, Pavel Tomancak
المصدر: ISBI
سنة النشر: 2019
مصطلحات موضوعية: FOS: Computer and information sciences, Computer Science - Machine Learning, Computer science, Calibration (statistics), Computer Vision and Pattern Recognition (cs.CV), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, Quantitative Biology - Quantitative Methods, Machine Learning (cs.LG), 03 medical and health sciences, Histogram, FOS: Electrical engineering, electronic engineering, information engineering, Quantitative Methods (q-bio.QM), 030304 developmental biology, Parametric statistics, 0303 health sciences, business.industry, Deep learning, Image and Video Processing (eess.IV), Probabilistic logic, Pattern recognition, Electrical Engineering and Systems Science - Image and Video Processing, 021001 nanoscience & nanotechnology, Mixture model, Noise, FOS: Biological sciences, Artificial intelligence, 0210 nano-technology, business
الوصف: Image denoising is the first step in many biomedical image analysis pipelines and Deep Learning (DL) based methods are currently best performing. A new category of DL methods such as Noise2Void or Noise2Self can be used fully unsupervised, requiring nothing but the noisy data. However, this comes at the price of reduced reconstruction quality. The recently proposed Probabilistic Noise2Void (PN2V) improves results, but requires an additional noise model for which calibration data needs to be acquired. Here, we present improvements to PN2V that (i) replace histogram based noise models by parametric noise models, and (ii) show how suitable noise models can be created even in the absence of calibration data. This is a major step since it actually renders PN2V fully unsupervised. We demonstrate that all proposed improvements are not only academic but indeed relevant.
Accepted at ISBI 2020
اللغة: English
URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1ce1bfe5de19b4ffc73bb4132ad91c2
http://arxiv.org/abs/1911.12291
حقوق: OPEN
رقم الأكسشن: edsair.doi.dedup.....d1ce1bfe5de19b4ffc73bb4132ad91c2
قاعدة البيانات: OpenAIRE