Deep Active Learning in the Open World

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Tian, Zhang, Jifan, Bai, Haoyue, Nowak, Robert
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917990269714432
author Xie, Tian
Zhang, Jifan
Bai, Haoyue
Nowak, Robert
author_facet Xie, Tian
Zhang, Jifan
Bai, Haoyue
Nowak, Robert
contents Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations. As AI systems advance and find application in safety-critical domains, effectively handling out-of-distribution (OOD) data is crucial to building open-world learning systems. In this work, we introduce ALOE, a novel active learning algorithm for open-world environments designed to enhance model adaptation by incorporating new OOD classes via a two-stage approach. First, diversity sampling selects a representative set of examples, followed by energy-based OOD detection to prioritize likely unknown classes for annotation. This strategy accelerates class discovery and learning, even under constrained annotation budgets. Evaluations on three long-tailed image classification benchmarks demonstrate that ALOE outperforms traditional active learning baselines, effectively expanding known categories while balancing annotation cost. Our findings reveal a crucial tradeoff between enhancing known-class performance and discovering new classes, setting the stage for future advancements in open-world machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06353
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Active Learning in the Open World
Xie, Tian
Zhang, Jifan
Bai, Haoyue
Nowak, Robert
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations. As AI systems advance and find application in safety-critical domains, effectively handling out-of-distribution (OOD) data is crucial to building open-world learning systems. In this work, we introduce ALOE, a novel active learning algorithm for open-world environments designed to enhance model adaptation by incorporating new OOD classes via a two-stage approach. First, diversity sampling selects a representative set of examples, followed by energy-based OOD detection to prioritize likely unknown classes for annotation. This strategy accelerates class discovery and learning, even under constrained annotation budgets. Evaluations on three long-tailed image classification benchmarks demonstrate that ALOE outperforms traditional active learning baselines, effectively expanding known categories while balancing annotation cost. Our findings reveal a crucial tradeoff between enhancing known-class performance and discovering new classes, setting the stage for future advancements in open-world machine learning.
title Deep Active Learning in the Open World
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.06353