Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Boosting Active Learning via Improving Test Performance

About

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.

Tianyang Wang, Xingjian Li, Pengkun Yang, Guosheng Hu, Xiangrui Zeng, Siyu Huang, Cheng-Zhong Xu, Min Xu• 2021

Related benchmarks

TaskDatasetResultRank
Medical Image ClassificationFed-ISIC Round 2
BMA63.23
19
Medical Image ClassificationFed-ISIC (Round 5)
Balanced Accuracy66.52
19
Medical Image ClassificationFed-Camelyon (Round 5)
Accuracy95.92
19
Lesion SegmentationIn-house CT dataset (test)
Pixel-wise Dice70.54
14
Showing 4 of 4 rows

Other info

Follow for update