activity
20182025
most citedHalf a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning

143 citations · 194 across the 8 of their papers we have counts for

collaborators
Showing 2018Show all

5 papers · 1 filter

cs.CV2018

Scale equivariance in CNNs with vector fields

Diego Marcos, Benjamin Kellenberger, Sylvain Lobry +1

We study the effect of injecting local scale equivariance into Convolutional Neural Networks. This is done by applying each convolutional filter at multiple scales. The output is a…

cs.CV2018

Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning

Benjamin Kellenberger, Diego Marcos, Devis Tuia

Knowledge over the number of animals in large wildlife reserves is a vital necessity for park rangers in their efforts to protect endangered species. Manual animal censuses are dan…

cs.CV2018

Learning deep structured active contours end-to-end

Diego Marcos, Devis Tuia, Benjamin Kellenberger +4

The world is covered with millions of buildings, and precisely knowing each instance's position and extents is vital to a multitude of applications. Recently, automated building fo…

cs.CV2018

Land cover mapping at very high resolution with rotation equivariant CNNs: towards small yet accurate models

Diego Marcos, Michele Volpi, Benjamin Kellenberger +1

In remote sensing images, the absolute orientation of objects is arbitrary. Depending on an object's orientation and on a sensor's flight path, objects of the same semantic class c…

cs.CV2018

DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation

Bharath Bhushan Damodaran, Benjamin Kellenberger, Rémi Flamary +2

In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar cha…