Online Representation Learning on the Open Web

• This repository was created by Ellis Brown and contains the full source code to produce my master's thesis document.
• The thesis defense can be viewed on YouTube. Slides are available here.

Publications behind this thesis

Some of the content here is behind these publications:

Internet Explorer: Targeted Representation Learning on the Open Web Alexander C. Li*, Ellis Brown*, Alexei A. Efros, Deepak Pathak [1] [web] [arXiv] [pdf] [code]

Your Diffusion Model is Secretly a Zero-Shot Classifier Alexander C. Li, Mihir Prabhudesai, Shivam Duggal, Ellis Brown, and Deepak Pathak [2] [web] [arXiv] [pdf] [code]

---

The experimental source code and libraries produced for this thesis are freely available as open source software and are available in the following repository.

• internet-explorer-ssl/internet-explorer — Internet Explorer explores the web in a self-supervised manner to progressively find relevant examples that improve performance on a desired target dataset.
• ellisbrown/google-images-download — Download images from Google Images.
• ellisbrown/IN100 — Code to generate an ImageNet-100 subset using symlinks to an existing ImageNet installation.

---

• This repository started from Brandon Amos's great thesis repo, which was based on Cyrus Omar's thesis code, which, in turn, was based on a CMU thesis template by David Koes and others before.

---

The BibTeX for this document is:

@mastersthesis{brown2023online,
  author       = {Ellis Brown},
  title        = {Online Representation Learning on the Open Web},
  school       = {Carnegie Mellon University},
  year         = 2023,
  month        = May,
}