University of Illinois Urbana-Champaign

INVESTIGATING COLD-START FAILURE IN ACTIVE LEARNING FOR IMAGES

Erickson, Emma

Content Files
SP21-ECE499-Thesis-Erickson, Emma.pdf

Permalink

https://hdl.handle.net/2142/124954

Description

Title
INVESTIGATING COLD-START FAILURE IN ACTIVE LEARNING FOR IMAGES
Author(s)
Erickson, Emma
Issue Date
2021-05-01
Keyword(s)
Active Learning; Cold-start Failure; Image Classification
Date of Ingest
2024-10-24T12:09:35-05:00
Abstract
Active learning is a machine learning strategy which seeks to achieve the best possible results with the fewest labeled examples. When successful, active learning improves model performance at a lower labeling cost than labeling randomly or uniformly. However, if these active learning strategies are employed too early, active learning may perform worse than random selection, a condition known as cold-start failure. This thesis first characterizes the problem of cold-start failure in image classification, examining the training conditions under which cold-start failure occurs using the MNIST dataset. Following this, behaviors and selections of active learning strategies under cold-start are analyzed and compared to training behavior in both uniform sampling and successful active learning situations. Finally, self-supervision strategies are introduced to generate new features from the images within the unlabeled pool in an attempt to alleviate cold-start failure and allow active learning training to successfully begin earlier. We did not find evidence that this additional feature extraction was useful in alleviating cold-start failure for our dataset.
Type of Resource
text
Genre of Resource
dissertation/thesis
Language
eng

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research