research
∙
01/05/2023
Teaching Computer Vision for Ecology
Computer vision can accelerate ecology research by automating the analys...
share
research
∙
11/08/2022
Fine-grained Population Mapping from Coarse Census Counts and Open Geodata
Fine-grained population maps are needed in several domains, like urban p...
research
∙
10/25/2021
Seeing biodiversity: perspectives in machine learning for wildlife conservation
Data acquisition in animal ecology is rapidly accelerating due to inexpe...
research
∙
09/24/2021
How to find a good image-text embedding for remote sensing visual question answering?
Visual question answering (VQA) has recently been introduced to remote s...
research
∙
08/17/2021
Self-Supervised Pretraining and Controlled Augmentation Improve Rare Wildlife Recognition in UAV Images
Automated animal censuses with aerial imagery are a vital ingredient tow...
research
∙
07/29/2021
Mapping Vulnerable Populations with AI
Humanitarian actions require accurate information to efficiently delegat...
research
∙
07/17/2019
Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning
We present an Active Learning (AL) strategy for re-using a deep Convolut...
research
∙
07/31/2018
Scale equivariance in CNNs with vector fields
We study the effect of injecting local scale equivariance into Convoluti...
research
∙
06/29/2018
Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning
Knowledge over the number of animals in large wildlife reserves is a vit...
research
∙
03/27/2018
DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation
In computer vision, one is often confronted with problems of domain shif...
research
∙
03/16/2018
Learning deep structured active contours end-to-end
The world is covered with millions of buildings, and precisely knowing e...
research
∙
03/16/2018