Me.

Isay Katsman

I'm a Computer Science and Math double major undergraduate student at Cornell University advised by Serge Belongie. My research interests include machine learning and computer vision, particularly in the context of security (adversarial examples) and generative modeling.

I am actively seeking PhD advisors for Fall 2020.

Email: isk22@cornell.edu [Google Scholar] [LinkedIn] [Github]

News

  • November 2019: Cornell Chronicle press release about ILA (ICCV 2019 paper) published.
  • August 2019: Finished internship at Facebook AI under Prof. Kristen Grauman.
  • July 2019: Two papers accepted by ICCV 2019.

Publications


Conference Papers

(ICCV 2019) Enhancing Adversarial Example Transferability with an Intermediate Level Attack [Arxiv]

Qian Huang*, Isay Katsman*, Horace He*, Zeqi Gu*, Serge Belongie, Ser-Nam Lim

(ICCV 2019) Fashion++: Minimal Edits for Outfit Improvement [Arxiv] [Project Page] [Press Release] [Code]

Wei-Lin Hsiao, Isay Katsman*, Chao-Yuan Wu*, Devi Parikh, Kristen Grauman

(CVPR 2018) Generative Adversarial Perturbations [Link] [Code]

Omid Poursaeed, Isay Katsman, Bicheng Gao, Serge Belongie

Workshop Papers

(ICML 2019 Workshop, Security and Privacy of Machine Learning) Adversarial Example Decomposition [Arxiv]

Horace He, Aaron Lou*, Qingxuan Jiang*, Isay Katsman*, Serge Belongie, Ser-Nam Lim

(ICML 2018 Workshop, Vision with Biased or Scarce Data) Semantic Segmentation with Scarce Data [Arxiv]

Isay Katsman*, Rohun Tripathi*, Andreas Veit, Serge Belongie

*indicates equal contribution

Experience


Facebook

Research Intern
May 2019 - Aug 2019

Working with Prof. Kristen Grauman.

Facebook

Software Engineer Intern
May 2018 - Aug 2018

Intern on Facebook AI Research (FAIR) team.

Foursquare

Software Engineering Intern
May 2017 - Aug 2017

Worked on building RNNs for large-scale venue data extraction.

Avigilon

Software Engineering Intern
May 2016 - Aug 2016, May 2015 - Aug 2015

Worked on building Siamese and Triplet networks for appearance-based similarity learning.


Leadership


Cornell University Vision and Learning (CUVL)

Co-president
Aug 2018 - present
Official Club Website
Press Release

Founded a club focused on undergraduate research and education in the fields of computer vision and machine learning. The club is funded by and works directly with Facebook AI.


Service and Awards


Reviewing:

  • Accepted invitation to review for ICML 2020
  • Accepted invitation to review for CVPR 2020
  • ICCV 2019 Secondary Reviewer
  • CVPR 2019 Secondary Reviewer

Awards:

  • 2019 CRA Award for Outstanding Undergraduate Researchers - Honorable Mention