On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “FROC-score”

S4ND: Single-Shot Single-Scale Lung Nodule Detectioncs.CV

S4ND detects lung nodules faster and more accurately.

problem Efficient lung nodule detection from CT scans.

method Single-Shot Single-Scale 3D Convolutional Neural Network (CNN) trained end-to-end.

result S4ND outperforms state-of-the-art methods in terms of efficiency and accuracy.

lung nodule detection deep learning 3D CNN FROC-score CT scans

2018-05-06abs ↗pdf ↗

3D G-CNNs for Pulmonary Nodule Detectioncs.LG

3D G-CNNs reduce false positives in lung nodule detection.

problem Reducing false positives in pulmonary nodule detection.

method Used 3D roto-translation group convolutions (G-Convs) instead of traditional convolutions.

result 3D G-CNNs achieved FROC scores close to those of a CNN trained on ten times more data.

3D CNNs Pulmonary Nodules False Positives Medical Imaging Convolutional Neural Networks

2018-04-12abs ↗pdf ↗