Edo Collins

Office: BC 316
Email: edo [dot] collins [at] epfl [dot] ch
Postal address: BC 316 (Bâtiment BC)
Station 14
CH-1015 Lausanne

Update: I have graduated and am currently working at the Computer Vision group at Xerox PARC.


  • 2014 – 2019: PhD student at IVRL, EPFL, Switzerland
  • 2011 – 2014: Master’s in Computational Linguistics at Universität Tübingen, Germany
  • 2005 – 2009: Bachelor’s in Computer Science at The Open University of Israel

Work Experience

  • 2012 – 2014: Research assistant at Department of Computational Linguistics, Uni Tübingen, Germany
  • 2007 – 2011: Software developer at eWave, Israel
  • 2005 – 2007: Software developer at Visa-Cal, Israel


  • E. Collins and S. Süsstrunk. Deep Feature Factorization for Content-based Image Retrieval and Localization. In IEEE International Conference on Image Processing (ICIP), 2019. [Project page]
  • E. Collins, S. A. Bigdeli, and S. Süsstrunk. Detecting Memorization in ReLU Networks. arXiv preprint arXiv:1810.03372 (2018). [Paper]
  • E. Collins, R. Achanta and S. Süsstrunk. Deep Feature Factorization For Concept Discovery. In European Conference on Computer Vision (ECCV), 2018. [Project page]
  • W. J. Haaswijk, E. Collins, B. Seguin et al. Deep Learning for Logic Optimization Algorithms. In IEEE International Symposium on Circuits and Systems (ISCAS), 2018.
  • M. Engilberge, E. Collins S. Süsstrunk. Color Representation in Deep Neural Networks. In IEEE International Conference on Image Processing (ICIP), 2017.
  • D. Carlson, Y.-P. Hsieh, E. Collins, L. Carin, V. Cevher. Stochastic Spectral Descent for Discrete Graphical Models. In IEEE Journal of Selected Topics in Signal Processing (J-STSP), 2016
  • D. Carlson, E. Collins, Y.-P. Hsieh, L. Carin, V. Cevher. Preconditioned Spectral Descent for Deep Learning. In 29th Neural Information Processing Systems (NIPS), 2015.