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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Xavier Boix

Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss


Oct 30, 2021
Akira Sakai, Taro Sunagawa, Spandan Madan, Kanata Suzuki, Takashi Katoh, Hiromichi Kobashi, Hanspeter Pfister, Pawan Sinha, Xavier Boix, Tomotake Sasaki


  Access Paper or Ask Questions

To Which Out-Of-Distribution Object Orientations Are DNNs Capable of Generalizing?


Sep 28, 2021
Avi Cooper, Xavier Boix, Daniel Harari, Spandan Madan, Hanspeter Pfister, Tomotake Sasaki, Pawan Sinha


  Access Paper or Ask Questions

The Foes of Neural Network's Data Efficiency Among Unnecessary Input Dimensions


Jul 13, 2021
Vanessa D'Amario, Sanjana Srivastava, Tomotake Sasaki, Xavier Boix


  Access Paper or Ask Questions

Small in-distribution changes in 3D perspective and lighting fool both CNNs and Transformers


Jun 30, 2021
Spandan Madan, Tomotake Sasaki, Tzu-Mao Li, Xavier Boix, Hanspeter Pfister


  Access Paper or Ask Questions

How Modular Should Neural Module Networks Be for Systematic Generalization?


Jun 15, 2021
Vanessa D'Amario, Tomotake Sasaki, Xavier Boix


  Access Paper or Ask Questions

On the Capability of Neural Networks to Generalize to Unseen Category-Pose Combinations


Jul 15, 2020
Spandan Madan, Timothy Henry, Jamell Dozier, Helen Ho, Nishchal Bhandari, Tomotake Sasaki, Frédo Durand, Hanspeter Pfister, Xavier Boix


  Access Paper or Ask Questions

Is Robustness To Transformations Driven by Invariant Neural Representations?


Jul 02, 2020
Syed Suleman Abbas Zaidi, Xavier Boix, Neeraj Prasad, Sharon Gilad-Gutnick, Shlomit Ben-Ami, Pawan Sinha


  Access Paper or Ask Questions

Removable and/or Repeated Units Emerge in Overparametrized Deep Neural Networks


Dec 21, 2019
Stephen Casper, Xavier Boix, Vanessa D'Amario, Ling Guo, Martin Schrimpf, Kasper Vinken, Gabriel Kreiman


  Access Paper or Ask Questions

Minimal Images in Deep Neural Networks: Fragile Object Recognition in Natural Images


Feb 08, 2019
Sanjana Srivastava, Guy Ben-Yosef, Xavier Boix

* International Conference on Learning Representations (ICLR) 2019 

  Access Paper or Ask Questions

Theory IIIb: Generalization in Deep Networks


Jun 29, 2018
Tomaso Poggio, Qianli Liao, Brando Miranda, Andrzej Banburski, Xavier Boix, Jack Hidary

* 38 pages, 7 figures 

  Access Paper or Ask Questions

Theory of Deep Learning III: explaining the non-overfitting puzzle


Jan 16, 2018
Tomaso Poggio, Kenji Kawaguchi, Qianli Liao, Brando Miranda, Lorenzo Rosasco, Xavier Boix, Jack Hidary, Hrushikesh Mhaskar


  Access Paper or Ask Questions

Herding Generalizes Diverse M -Best Solutions


Jan 30, 2017
Ece Ozkan, Gemma Roig, Orcun Goksel, Xavier Boix

* 8 pages, 2 algorithms, 3 figures 

  Access Paper or Ask Questions

Foveation-based Mechanisms Alleviate Adversarial Examples


Jan 19, 2016
Yan Luo, Xavier Boix, Gemma Roig, Tomaso Poggio, Qi Zhao


  Access Paper or Ask Questions

Comment on "Ensemble Projection for Semi-supervised Image Classification"


Aug 29, 2014
Xavier Boix, Gemma Roig, Luc Van Gool


  Access Paper or Ask Questions

Random Binary Mappings for Kernel Learning and Efficient SVM


Mar 28, 2014
Gemma Roig, Xavier Boix, Luc Van Gool


  Access Paper or Ask Questions

SEEDS: Superpixels Extracted via Energy-Driven Sampling


Sep 16, 2013
Michael Van den Bergh, Xavier Boix, Gemma Roig, Luc Van Gool


  Access Paper or Ask Questions