Long-tailed image recognition
BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images. 
| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://jkozerawski.github.io/research/
access-control-allow-origin: *
expires: Mon, 29 Dec 2025 05:27:46 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: 274D:3157C7:83EFC8:946E56:69520EFA
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 05:17:46 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210038-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766985466.246922,VS0,VE219
vary: Accept-Encoding
x-fastly-request-id: 210a9954fff31cc6128f2f056436e49317ba741a
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sat, 25 Sep 2021 23:58:15 GMT
access-control-allow-origin: *
etag: W/"614fb797-28db"
expires: Mon, 29 Dec 2025 05:27:46 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 73F6:2D8B9D:84BD21:953C13:69520EFA
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 05:17:46 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210038-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766985466.484619,VS0,VE209
vary: Accept-Encoding
x-fastly-request-id: af26f362eee9d03d7cc29ffb5959317570968b5c
content-length: 3047
Research - Jedrzej Kozerawski 
Jedrzej (Jacob) Kozerawski
Postdoc @UCSD | PhD in Computer Vision/Machine Learning from UCSB
- San Diego, CA
- UC San Diego
- ResearchGate
- Github
- Google Scholar
Research
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.