Boosting Active Learning via Improving Test Performance

TL;DR

This paper introduces a novel active learning framework that improves test performance by selecting unlabeled data based on gradient norm estimates, validated across multiple tasks including image classification, segmentation, and cellular imaging.

Contribution

It proposes two schemes, expected-gradnorm and entropy-gradnorm, to estimate gradient norms for unlabeled data, enhancing active learning effectiveness.

Findings

Achieves superior performance over state-of-the-art methods.

Effective across diverse tasks including image classification and cellular imaging.

Demonstrates robustness to noise and domain shifts.

Abstract

Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless, it remains unclear how selected data impacts the test performance of the task model used in AL. In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in better test performance. However, due to the lack of label information, directly computing gradient norm for unlabeled data is infeasible. To address this challenge, we propose two schemes, namely expected-gradnorm and entropy-gradnorm. The former computes the gradient norm by constructing an expected empirical loss while the latter constructs an unsupervised loss with entropy. Furthermore, we integrate the two schemes in a universal AL framework. We evaluate our method on classical image classification and semantic segmentation tasks. To demonstrate its competency in domain applications and its robustness to noise, we also validate our method on a cellular imaging analysis task, namely cryo-Electron Tomography subtomogram classification. Results demonstrate that our method achieves superior performance against the state of the art. Our source code is available at https://github.com/xulabs/aitom/blob/master/doc/projects/al_gradnorm.md.