Benchmarking of Query Strategies: Towards Future Deep Active Learning
Not on the map. Why?
Abstract (arXiv)
In this study, we benchmark query strategies for deep actice learning~(DAL). DAL reduces annotation costs by annotating only high-quality samples selected by query strategies. Existing research has two main problems, that the experimental settings are not standardized, making the evaluation of existing methods is difficult, and that most of experiments were conducted on the CIFAR or MNIST datasets. Therefore, we develop standardized experimental settings for DAL and investigate the effectiveness of various query strategies using six datasets, including those that contain medical and visual inspection images. In addition, since most current DAL approaches are model-based, we perform verification experiments using fully-trained models for querying to investigate the effectiveness of these approaches for the six datasets. Our code is available at hrefhttps://github.com/ia-gu/Benchmarking-of-Query-Strategies-Towards-Future-Deep-Active-Learning
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 53 of its 79 references that are in the map. First posted on arXiv 10 Dec 2023.
Builds on
53 of 79 references.
References · 53
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2020Exploring Simple Siamese Representation Learningcited by 2,853
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
- 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
- 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
- 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
38 more
- 2017Deep Bayesian Active Learning with Image Datacited by 812
- 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
- 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
- 2020A Survey on Contrastive Self-supervised Learningcited by 553
- 2020A Survey of Deep Active Learningcited by 547
- 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
- 2019Learning Loss for Active Learningcited by 335
- 2019Variational Adversarial Active Learningcited by 284
- 2020GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learningcited by 224
- 2016Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learningcited by 193
- 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
- 2020Bayesian Neural Networks: An Introduction and Surveycited by 130
- 2021Batch Active Learning at Scalecited by 127
- 2021Self-Supervised Learning with Swin Transformerscited by 121
- 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
- 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
- 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 92
- 2019Diverse mini-batch Active Learningcited by 88
- 2020Submodular Combinatorial Information Measures with Applications in Machine Learningcited by 88
- 2020Task-Aware Variational Adversarial Active Learningcited by 84
- 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
- 2017Deep Active Learning over the Long Tailcited by 82
- 2020Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunitiescited by 71
- 2017Generative Adversarial Active Learningcited by 69
- 2019Selfie: Self-supervised Pretraining for Image Embeddingcited by 46
- 2021Effective Evaluation of Deep Active Learning on Image Classification Taskscited by 37
- 2018OCTID: Optical Coherence Tomography Image Databasecited by 36
- 2018Addressing the Item Cold-start Problem by Attribute-driven Active Learningcited by 33
- 2021Consistency-based Active Learning for Object Detectioncited by 32
- 2022Making Your First Choice: To Address Cold Start Problem in Vision Active Learningcited by 25
- 2021Class-Balanced Active Learning for Image Classificationcited by 15
- 2018Deep Active Learning for Anomaly Detectioncited by 10
- 2022Patient Aware Active Learning for Fine-Grained OCT Classificationcited by 9
- 2020Identifying Wrongly Predicted Samples: A Method for Active Learningcited by 8
- 2023Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Datacited by 8
- 2020Data-efficient Online Classification with Siamese Networks and Active Learningcited by 7
- 2021ActiveMatch: End-to-end Semi-supervised Active Representation Learningcited by 6
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.