Boosting Active Learning with Knowledge Transfer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Tianyang, Xiao, Xi, Chen, Gaofei, Liao, Xiaoying, Cheng, Guo, Ji, Yingrui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909797650006016
author Wang, Tianyang
Xiao, Xi
Chen, Gaofei
Liao, Xiaoying
Cheng, Guo
Ji, Yingrui
author_facet Wang, Tianyang
Xiao, Xi
Chen, Gaofei
Liao, Xiaoying
Cheng, Guo
Ji, Yingrui
contents Uncertainty estimation is at the core of Active Learning (AL). Most existing methods resort to complex auxiliary models and advanced training fashions to estimate uncertainty for unlabeled data. These models need special design and hence are difficult to train especially for domain tasks, such as Cryo-Electron Tomography (cryo-ET) classification in computational biology. To address this challenge, we propose a novel method using knowledge transfer to boost uncertainty estimation in AL. Specifically, we exploit the teacher-student mode where the teacher is the task model in AL and the student is an auxiliary model that learns from the teacher. We train the two models simultaneously in each AL cycle and adopt a certain distance between the model outputs to measure uncertainty for unlabeled data. The student model is task-agnostic and does not rely on special training fashions (e.g. adversarial), making our method suitable for various tasks. More importantly, we demonstrate that data uncertainty is not tied to concrete value of task loss but closely related to the upper-bound of task loss. We conduct extensive experiments to validate the proposed method on classical computer vision tasks and cryo-ET challenges. The results demonstrate its efficacy and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15805
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Boosting Active Learning with Knowledge Transfer
Wang, Tianyang
Xiao, Xi
Chen, Gaofei
Liao, Xiaoying
Cheng, Guo
Ji, Yingrui
Computer Vision and Pattern Recognition
Uncertainty estimation is at the core of Active Learning (AL). Most existing methods resort to complex auxiliary models and advanced training fashions to estimate uncertainty for unlabeled data. These models need special design and hence are difficult to train especially for domain tasks, such as Cryo-Electron Tomography (cryo-ET) classification in computational biology. To address this challenge, we propose a novel method using knowledge transfer to boost uncertainty estimation in AL. Specifically, we exploit the teacher-student mode where the teacher is the task model in AL and the student is an auxiliary model that learns from the teacher. We train the two models simultaneously in each AL cycle and adopt a certain distance between the model outputs to measure uncertainty for unlabeled data. The student model is task-agnostic and does not rely on special training fashions (e.g. adversarial), making our method suitable for various tasks. More importantly, we demonstrate that data uncertainty is not tied to concrete value of task loss but closely related to the upper-bound of task loss. We conduct extensive experiments to validate the proposed method on classical computer vision tasks and cryo-ET challenges. The results demonstrate its efficacy and efficiency.
title Boosting Active Learning with Knowledge Transfer
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.15805