Elijah Cole

Ph.D. Candidate at Caltech

Email / Google Scholar / Twitter / LinkedIn / CV

I'm a final-year Ph.D. candidate in the Computing and Mathematical Sciences department at Caltech. My advisor is Pietro Perona.

Research: My goal is to create algorithms that amplify the abilities of scientists, doctors, and other human experts. My work bridges the gap between traditional machine learning techniques and the challenges faced by human experts, including fine-grained categories, heterogeneous side information, and scarce/noisy/biased labels. I also use these real-world problems as the basis for new benchmark datasets, which measure algorithmic innovation in terms of progress on impactful applications. My work is supported in part by an NSF Graduate Research Fellowship and an Explorer Grant from the Resnick Sustainability Institute.

Previously: I graduated from Duke University in 2017 with a B.S.E. in Electrical and Computer Engineering and Mathematics. I've also spent time at Google Research, Microsoft Research, the Air Force Research Lab, the Duke University Marine Lab, and the Woods Hole Oceanographic Institution. I'm a proud product of public schools in Utah (Grantsville, Sandy, Salt Lake City), Nebraska (Omaha), and Texas (San Antonio).

I am on the 2022-2023 job market! Email is the best way to reach me.

Selected Publications

For a complete list, please see my Google Scholar page.


On Label Granularity and Object Localization
E. Cole, K. Wilber, G. Van Horn, X. Yang, M. Fornoni, P. Perona, S. Belongie, A. Howard, and O. Mac Aodha
ECCV 2022
Paper Data


When Does Contrastive Visual Representation Learning Work?
E. Cole, X. Yang, K. Wilber, O. Mac Aodha, S. Belongie
CVPR 2022
Paper Website


Multi-Label Learning from Single Positive Labels
E. Cole, O. Mac Aodha, T. Lorieul, P. Perona, D. Morris, N. Jojic
CVPR 2021
Paper Code Video


Benchmarking Representation Learning for Natural World Image Collections
G. Van Horn, E. Cole, S. Beery, K. Wilber, S. Belongie, O. Mac Aodha
CVPR 2021 (Oral)
Paper Code+Data Video


Species Distribution Modeling for Machine Learning Practitioners: A Review
S. Beery*, E. Cole*, J. Parker, P. Perona, K. Winner


Presence-Only Geographical Priors for Fine-Grained Image Classification
O. Mac Aodha, E. Cole, P. Perona
ICCV 2019
Paper Code Video


Large-scale dataset of animal images for object localization.

Large-scale dataset for fine-grained species classification.
2021 Dataset

A suite of ecologically-inspired classification tasks for evaluating self-supervised learning in realistic use cases.
2021 Dataset

Datasets for camera trap image analysis.
2021 Dataset 2020 Dataset

Dataset for species distribution modeling with remote sensing imagery.
2020 Dataset



Resnick Sustainability Institute Summer School on Computer Vision Methods for Ecology
Caltech | Instructor Summer 2022

A three-week intensive summer school teaching computer vision methods for ecology and seeking to empower ecologists to accurately and efficiently analyze large image, audio, or video datasets using computer vision.

EE/CS/CNS 148b: Selected Topics in Computational Vision
Caltech | Graduate TA Spring 2022 Spring 2021 Spring 2020

An introduction to essential topics in modern computer vision, ranging from state-of-the-art algorithms to ethics. Students also learn how to use tools like cloud computing and crowdsourcing to accelerate computer vision projects.


Research and Publishing in Computer Vision
EE/CNS/CS 148: Selected Topics in Computational Vision, Caltech
May 12, 2022

A Conceptual Introduction to Computer Vision for Remote Sensing
AILA Open Innovation Challenge Kick-Off Day, Bioscience LA
March 19, 2022

Unsupervised and Self-Supervised Learning
EE/CNS/CS 148: Selected Topics in Computational Vision, Caltech
May 14, 2020

Plain Academic