scispace - formally typeset
R

Raghavendra Selvan

Researcher at University of Copenhagen

Publications -  44
Citations -  629

Raghavendra Selvan is an academic researcher from University of Copenhagen. The author has contributed to research in topics: Tensor & Image segmentation. The author has an hindex of 8, co-authored 44 publications receiving 271 citations.

Papers
More filters
Posted Content

Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models

TL;DR: This work proposes that energy and carbon footprint of model development and training is reported alongside performance metrics using tools like Carbontracker, and hopes this will promote responsible computing in ML and encourage research into energy-efficient deep neural networks.
Journal ArticleDOI

Segmentation of roots in soil with U-Net.

TL;DR: In this article, an automated image segmentation method based on the U-Net Convolutional Neural Network (CNN) architecture was proposed for root detection and quantification in soil images.
Book ChapterDOI

A Joint 3D UNet-Graph Neural Network-Based Method for Airway Segmentation from Chest CTs

TL;DR: An end-to-end deep learning segmentation method by combining a 3D UNet architecture with a graph neural network (GNN) model with two types of graph adjacency, which is applied to the task of segmenting the airway tree from chest CT scans.
Posted Content

Lung Segmentation from Chest X-rays using Variational Data Imputation

TL;DR: This work treats the high opacity regions of lungs from such abnormal CXRs as missing data and presents a modified CNN-based image segmentation network that utilizes a deep generative model for data imputation.