# Boosting Active Learning via Improving Test Performance

arXiv: https://arxiv.org/abs/2112.05683 · HTML: https://mlsanity.com/paper/2112.05683/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 54 references that are in the map.
- First posted on arXiv 10 Dec 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Stronger generalization bounds for deep nets via a compression approach](https://mlsanity.com/paper/1802.05296/) (2018)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Adversarial Active Learning for Deep Networks: a Margin Based Approach](https://mlsanity.com/paper/1802.09841/) (2018)
- [A General Framework for Uncertainty Estimation in Deep Learning](https://mlsanity.com/paper/1907.06890/) (2019)
- [Learning Active Learning from Data](https://mlsanity.com/paper/1703.03365/) (2017)
- [Influence Selection for Active Learning](https://mlsanity.com/paper/2108.09331/) (2021)
- [Knowledge Transfer with Jacobian Matching](https://mlsanity.com/paper/1803.00443/) (2018)
- [Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network](https://mlsanity.com/paper/1806.05473/) (2018)
- [Generative Adversarial Active Learning](https://mlsanity.com/paper/1702.07956/) (2017)
- [Sequential Graph Convolutional Network for Active Learning](https://mlsanity.com/paper/2006.10219/) (2020)
- [State-Relabeling Adversarial Active Learning](https://mlsanity.com/paper/2004.04943/) (2020)
- [Adversarial Sampling for Active Learning](https://mlsanity.com/paper/1808.06671/) (2018)
- [Cost-Effective Active Learning for Melanoma Segmentation](https://mlsanity.com/paper/1711.09168/) (2017)
- [Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection](https://mlsanity.com/paper/1809.02882/) (2018)
- [Hierarchical Subquery Evaluation for Active Learning on a Graph](https://mlsanity.com/paper/1504.08219/) (2015)
- [Deep Active Learning with Adaptive Acquisition](https://mlsanity.com/paper/1906.11471/) (2019)
- [Piecewise convexity of artificial neural networks](https://mlsanity.com/paper/1607.04917/) (2016)

## Built on by (most cited first, 19 of 19)

- [A Comparative Survey of Deep Active Learning](https://mlsanity.com/paper/2203.13450/) (2022)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts](https://mlsanity.com/paper/2312.02567/) (2023)
- [Deep Active Learning with Noise Stability](https://mlsanity.com/paper/2205.13340/) (2022)
- [Controllable Textual Inversion for Personalized Text-to-Image Generation](https://mlsanity.com/paper/2304.05265/) (2023)
- [Fairness Without Harm: An Influence-Guided Active Sampling Approach](https://mlsanity.com/paper/2402.12789/) (2024)
- [Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation](https://mlsanity.com/paper/2411.15763/) (2024)
- [Deep Active Learning for Computer Vision: Past and Future](https://mlsanity.com/paper/2211.14819/) (2022)
- [Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Model](https://mlsanity.com/paper/2405.12081/) (2024)
- [Deep Active Learning in the Presence of Label Noise: A Survey](https://mlsanity.com/paper/2302.11075/) (2023)
- [Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrieval](https://mlsanity.com/paper/2412.02310/) (2024)
- [Confidence-based federated distillation for vision-based lane-centering](https://mlsanity.com/paper/2306.03222/) (2023)
- [SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentation](https://mlsanity.com/paper/2308.04911/) (2023)
- [How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learning](https://mlsanity.com/paper/2308.08224/) (2023)
- [Deep Active Learning with Manifold-preserving Trajectory Sampling](https://mlsanity.com/paper/2410.15605/) (2024)
- [LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training](https://mlsanity.com/paper/2411.15217/) (2024)
- [Active Learning Guided by Efficient Surrogate Learners](https://mlsanity.com/paper/2301.02761/) (2023)
- [Goal-Oriented Influence-Maximizing Data Acquisition for Learning and Optimization](https://mlsanity.com/paper/2602.19578/) (2026)

## Abstract (arXiv)

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.