61 citations · 120 across the 10 of their papers we have counts for
8 papers · 1 filter
UCoDe: Unified Community Detection with Graph Convolutional Networks
Atefeh Moradan, Andrew Draganov, Davide Mottin +1
Community detection finds homogeneous groups of nodes in a graph. Existing approaches either partition the graph into disjoint, non-overlapping, communities, or determine only over…
Weakly-Supervised Cloud Detection with Fixed-Point GANs
Joachim Nyborg, Ira Assent
The detection of clouds in satellite images is an essential preprocessing task for big data in remote sensing. Convolutional neural networks (CNNs) have greatly advanced the state-…
TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation
Joachim Nyborg, Charlotte Pelletier, Sébastien Lefèvre +1
The recent developments of deep learning models that capture complex temporal patterns of crop phenology have greatly advanced crop classification from Satellite Image Time Series…
On Quantitative Evaluations of Counterfactuals
Frederik Hvilshøj, Alexandros Iosifidis, Ira Assent
As counterfactual examples become increasingly popular for explaining decisions of deep learning models, it is essential to understand what properties quantitative evaluation metri…
TextBenDS: a generic Textual data Benchmark for Distributed Systems
Ciprian-Octavian Truica, Elena Apostol, Jérôme Darmont +1
Extracting top-k keywords and documents using weighting schemes are popular techniques employed in text mining and machine learning for different analysis and retrieval tasks. The…
Learning by Design: Structuring and Documenting the Human Choices in Machine Learning Development
Simon Enni, Ira Assent
The influence of machine learning (ML) is quickly spreading, and a number of recent technological innovations have applied ML as a central technology. However, ML development still…
ECINN: Efficient Counterfactuals from Invertible Neural Networks
Frederik Hvilshøj, Alexandros Iosifidis, Ira Assent
Counterfactual examples identify how inputs can be altered to change the predicted class of a classifier, thus opening up the black-box nature of, e.g., deep neural networks. We pr…
A reproduction of Apple's bi-directional LSTM models for language identification in short strings
Mads Toftrup, Søren Asger Sørensen, Manuel R. Ciosici +1
Language Identification is the task of identifying a document's language. For applications like automatic spell checker selection, language identification must use very short strin…