Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Page not in menu
This is a page not in th emain menu
Posts
Post 1
Published:
To be updated.
publications
CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition
Published in CVPR, 2018
One-Shot One-Class classification using deep networks and SVMs.
Recommended citation: Kozerawski, Jedrzej, and Matthew Turk. (2018). "CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition" CVPR 2018. http://jkozerawski.github.io/files/CVPR_2018.pdf
BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images
Published in ACCV, 2020
Boosting the accuracy for the tail categories in long-tailed datasets with additional hallucinated hard examples.
Recommended citation: Kozerawski, Jedrzej, et al, (2020). "BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images" ACCV 2020. http://jkozerawski.github.io/files/ACCV_2020.pdf
One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification
Published in arXiv, 2021
Few-Shot Open-Set classification using meta-learning.
Recommended citation: Kozerawski, Jedrzej, and Matthew Turk. (2021). "One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification" arXiv preprint arXiv:2109.06859, 2021. http://jkozerawski.github.io/files/OCML.pdf
research
Long-tailed image recognition
BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images. 
One-Shot One-Class image recognition
CLEAR: Cumulative LEARning for one-shot one-class image recognition (CVPR 2018) 
One-shot / few-shot image recognition
Studying problem of decreasing the performance gap between one-shot and few-shot testing scenarios.
CNNs training analysis
Analyzing the impact of specific training examples on the develompent of neural network weights. Studying ways of ensuring better quality weight-learning and generalization abilitites.
Self-supervised dataset explainability
Utilizing external knowledge bases to find semantically-sound subcategories in an existing dataset in order to achieve higher decision-making explainability.
talks
SVM Transfer Learning for Object Recognition
Published:
Talk description coming soon.
Explaining concepts visually: continuous AI learning
Published:
Talk description coming soon.
Explaining concepts visually: a novel approach for general object recognition
Published:
Talk description coming soon.
teaching
Teaching Assistant for ECE 152A - Digital Design Principles
Undergraduate course, University of California Santa Barbara, ECE Department, 2016
Teaching Assistant for CS 165B - Machine Learning
Undergraduate course, University of California Santa Barbara, CS Department, 2019
Teaching Assistant for ECE 181 - Introduction to Computer Vision
Undergraduate course, University of California Santa Barbara, ECE Department, 2020
Teaching Associate for CS 32 - Object Oriented Design and Principles
Undergraduate course, University of California Santa Barbara, CS Department, 2020
Link to the website in here
Section Leader for CS 106a - Code in Place
Undergraduate course, Stanford University, CS Department, 2020
Link to the website in here
Teaching Associate for INT 93 LS (Summer Research Academies) - Thinking Machines: A Dive into the Modern AI
Pre-college course, University of California Santa Barbara, Summer Sessions, 2020
Link to the lab activities here
Teaching Associate for CS 165B - Machine Learning
Undergraduate course, University of California Santa Barbara, CS Department, 2020
Teaching Associate for CS 32 - Object Oriented Design and Principles
Undergraduate course, University of California Santa Barbara, CS Department, 2020
Link to the website in here