Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation


Apr 19, 2021
Linara Adilova, Elena Schulz, Maram Akila, Sebastian Houben, Jan David Schneider, Fabian Hueger, Tim Wirtz

Add code

* Published at SAIAD (Safe Artificial Intelligence for Automated Driving) workshop at CVPR2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Novelty Detection in Sequential Data by Informed Clustering and Modeling


Mar 05, 2021
Linara Adilova, Siming Chen, Michael Kamp

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Resource-Constrained On-Device Learning by Dynamic Averaging


Sep 25, 2020
Lukas Heppe, Michael Kamp, Linara Adilova, Danny Heinrich, Nico Piatkowski, Katharina Morik

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Feature-Robustness, Flatness and Generalization Error for Deep Neural Networks


Jan 07, 2020
Henning Petzka, Linara Adilova, Michael Kamp, Cristian Sminchisescu

Add code

* arXiv admin note: substantial text overlap with arXiv:1912.00058 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Reparameterization-Invariant Flatness Measure for Deep Neural Networks


Nov 29, 2019
Henning Petzka, Linara Adilova, Michael Kamp, Cristian Sminchisescu

Add code

* 14 pages; accepted at Workshop "Science meets Engineering of Deep Learning", 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Information-Theoretic Perspective of Federated Learning


Nov 15, 2019
Linara Adilova, Julia Rosenzweig, Michael Kamp

Add code

* 5 pages, 8 figures Workshop on Information Theory and Machine Learning, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

System Misuse Detection via Informed Behavior Clustering and Modeling


Jul 01, 2019
Linara Adilova, Livin Natious, Siming Chen, Olivier Thonnard, Michael Kamp

Add code

* 9 pages including appendix, DSN Workshop on Data-Centric Dependability and Security (http://dcds.lasige.di.fc.ul.pt/

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Introducing Noise in Decentralized Training of Neural Networks


Sep 27, 2018
Linara Adilova, Nathalie Paul, Peter Schlicht

Add code

* ECML PKDD 2018, Workshop DMLE 
* 13 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Making Efficient Use of a Domain Expert's Time in Relation Extraction


Jul 12, 2018
Linara Adilova, Sven Giesselbach, Stefan Rüping

Add code

* DMNLP Workshop paper, ECML-PKDD 2017 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Efficient Decentralized Deep Learning by Dynamic Model Averaging


Jul 09, 2018
Michael Kamp, Linara Adilova, Joachim Sicking, Fabian Hüger, Peter Schlicht, Tim Wirtz, Stefan Wrobel

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email