Cost-Effective Active Learning for Melanoma Segmentation

November 24, 2017 · Entered Twilight · 🏛 Neural Information Processing Systems

"No code URL or promise found in abstract"
"Derived repo from GitHub Pages (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: README.md, _config.yml, authors, logos, requirements.txt, src

Authors Marc Gorriz, Axel Carlier, Emmanuel Faure, Xavier Giro-i-Nieto arXiv ID 1711.09168 Category cs.CV: Computer Vision Citations 127 Venue Neural Information Processing Systems Repository https://github.com/marc-gorriz/CEAL-Medical-Image-Segmentation ⭐ 280 Last Checked 7 days ago

Abstract

We propose a novel Active Learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our contribution is a practical Cost-Effective Active Learning approach using dropout at test time as Monte Carlo sampling to model the pixel-wise uncertainty and to analyze the image information to improve the training performance. The source code of this project is available at https://marc-gorriz.github.io/CEAL-Medical-Image-Segmentation/ .