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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors


Jun 30, 2022
Federica Granese, Marine Picot, Marco Romanelli, Francisco Messina, Pablo Piantanida

* This paper has been accepted to appear in the Proceedings of the 2022 European Conference on Machine Learning and Data Mining (ECML-PKDD), 19th to the 23rd of September, Grenoble, France 

   Access Paper or Ask Questions

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

Model-Agnostic Few-Shot Open-Set Recognition


Jun 18, 2022
Malik Boudiaf, Etienne Bennequin, Myriam Tami, Celine Hudelot, Antoine Toubhans, Pablo Piantanida, Ismail Ben Ayed

* Under review. Code available at https://github.com/ebennequin/few-shot-open-set 

   Access Paper or Ask Questions

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

Learning Disentangled Textual Representations via Statistical Measures of Similarity


May 07, 2022
Pierre Colombo, Guillaume Staerman, Nathan Noiry, Pablo Piantanida

* ACL 2022 

   Access Paper or Ask Questions

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

Realistic Evaluation of Transductive Few-Shot Learning


Apr 24, 2022
Olivier Veilleux, Malik Boudiaf, Pablo Piantanida, Ismail Ben Ayed

* NeurIPS 2021. Code at https://github.com/oveilleux/Realistic_Transductive_Few_Shot 

   Access Paper or Ask Questions

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

Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning


Mar 30, 2022
Georg Pichler, Marco Romanelli, Leonardo Rey Vega, Pablo Piantanida

* 6 pages 

   Access Paper or Ask Questions

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

Leveraging Adversarial Examples to Quantify Membership Information Leakage


Mar 23, 2022
Ganesh Del Grosso, Hamid Jalalzai, Georg Pichler, Catuscia Palamidessi, Pablo Piantanida


   Access Paper or Ask Questions

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

Igeood: An Information Geometry Approach to Out-of-Distribution Detection


Mar 15, 2022
Eduardo Dadalto Camara Gomes, Florence Alberge, Pierre Duhamel, Pablo Piantanida

* Accepted in ICLR 2022 

   Access Paper or Ask Questions

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

KNIFE: Kernelized-Neural Differential Entropy Estimation


Feb 14, 2022
Georg Pichler, Pierre Colombo, Malik Boudiaf, Gunther Koliander, Pablo Piantanida


   Access Paper or Ask Questions

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

InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation


Dec 13, 2021
Pierre Colombo, Chloe Clavel, Pablo Piantanida

* AAAI 2022 

   Access Paper or Ask Questions

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

PACMAN: PAC-style bounds accounting for the Mismatch between Accuracy and Negative log-loss


Dec 10, 2021
Matias Vera, Leonardo Rey Vega, Pablo Piantanida

* Submitted to be considered for publication in Information and Inference: a Journal of the IMA 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>