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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks


Dec 02, 2021
Guoxuan Xia, Sangwon Ha, Tiago Azevedo, Partha Maji

* Accepted at I (Still) Can't Believe It's Not Better Workshop at NeurIPS 2021 

   Access Paper or Ask Questions

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

On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications


Dec 01, 2021
Johanna Rock, Tiago Azevedo, René de Jong, Daniel Ruiz-Muñoz, Partha Maji

* 7 pages; Accepted at the Bayesian Deep Learning Workshop, NeurIPS 2021 

   Access Paper or Ask Questions

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

Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification


Aug 13, 2021
Shyam A. Tailor, René de Jong, Tiago Azevedo, Matthew Mattina, Partha Maji

* 8 pages. Accepted to the Deep Learning for Geometric Computing Workshop at ICCV 2021 

   Access Paper or Ask Questions

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

Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts


Sep 07, 2020
Tiago Azevedo, René de Jong, Partha Maji

* 9 pages, 7 figures 

   Access Paper or Ask Questions

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

Towards a predictive spatio-temporal representation of brain data


Feb 29, 2020
Tiago Azevedo, Luca Passamonti, Pietro Liò, Nicola Toschi

* To appear in the Workshop on AI for Affordable Healthcare (AI4AH) at ICLR 2020. 8 pages, 2 figures 

   Access Paper or Ask Questions

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