CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition
Kozerawski, Jedrzej, and Matthew Turk. (2018). "CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition" CVPR 2018.
CV
Education
- B.S. in GitHub, GitHub University, 2012
- M.S. in Jekyll, GitHub University, 2014
- Ph.D in Version Control Theory, GitHub University, 2018 (expected)
Work experience
- Summer 2015: Research Assistant
- Github University
- Duties included: Tagging issues
- Supervisor: Professor Git
- Fall 2015: Research Assistant
- Github University
- Duties included: Merging pull requests
- Supervisor: Professor Hub
Skills
- Skill 1
- Skill 2
- Sub-skill 2.1
- Sub-skill 2.2
- Sub-skill 2.3
- Skill 3
Publications
BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images
Kozerawski, Jedrzej, et al, (2020). "BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images" ACCV 2020.
One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification
Kozerawski, Jedrzej, and Matthew Turk. (2021). "One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification" arXiv preprint arXiv:2109.06859, 2021.
Talks
SVM Transfer Learning for Object Recognition
Talk at UC Santa Barbara, Society for Industrial and Applied Mathematics, Santa Barbara, California
Explaining concepts visually: continuous AI learning
Talk at UC Santa Barbara, CS Summit, Santa Barbara, California
Explaining concepts visually: a novel approach for general object recognition
Talk at UC Santa Barbara, Dynamical Neuroscience seminar, Santa Barbara, California
Teaching
Service and leadership
- Currently signed in to 43 different slack teams