Tagged in

Artificial Intelligence

The DownLinQ

As of March 2021, CosmiQ Works has been folded into IQT Labs. An archive will remain here to showcase historical work from CosmiQ Works that took place July 2016 — March 2021.

More information

Followers

1.6K

Elsewhere

More, on Medium

Artificial Intelligence

Jake Shermeyer in The DownLinQ

Mar 16, 2020

SpaceNet 6 Challenge Launch

Preface: SpaceNet LLC is a nonprofit organization dedicated to accelerating open source, artificial…

1 response

Daniel Hogan in The DownLinQ

Mar 5, 2020

The SpaceNet 6 Baseline

Preface: SpaceNet LLC is a nonprofit organization dedicated to accelerating open source, artificial intelligence…

2 responses

Adam Van Etten in The DownLinQ

Jan 23, 2020

SpaceNet 5 Results Deep Dive Part 2: APLS to APLS

Nick Weir in The DownLinQ

Jan 7, 2020

Viewing the world through a straw

How lessons from computer vision applications in geo will impact bio…

1 response

Daniel Hogan in The DownLinQ

Oct 16, 2019

Robustness of Limited Training Data: Part 5

Deep learning models for interpreting satellite imagery show increasing performance…

Daniel Hogan in The DownLinQ

Sep 25, 2019

Robustness of Limited Training Data: Part 4

When it comes to the relationship between geospatial neural network performance and…

Daniel Hogan in The DownLinQ

Jul 9, 2019

Robustness of Limited Training Data for Building Footprint Identification: Part 1

Nick Weir in The DownLinQ

Oct 29, 2018

A baseline model for the SpaceNet 4: Off-Nadir Building Detection Challenge

Lee Cohn in The DownLinQ

Apr 18, 2017

Object Segmentation on SpaceNet via Multi-task Network Cascades (MNC)

Patrick Hagerty in The DownLinQ

Mar 8, 2017

Super-Resolution on Satellite Imagery using Deep Learning, Part 3

In previous posts (Part 1 and Part 2), we trained a neural network to perform image enhancement using Peak Signal-to-Noise Ratio (PSNR) as a cost function and hypothesized that the enhancement will also improve object…