Enhancing Cost Efficiency in Active Learning with Candidate Set Query
Not on the map. Why?
Abstract (arXiv)
This paper introduces a cost-efficient active learning (AL) framework for classification, featuring a novel query design called candidate set query. Unlike traditional AL queries requiring the oracle to examine all possible classes, our method narrows down the set of candidate classes likely to include the ground-truth class, significantly reducing the search space and labeling cost. Moreover, we leverage conformal prediction to dynamically generate small yet reliable candidate sets, adapting to model enhancement over successive AL rounds. To this end, we introduce an acquisition function designed to prioritize data points that offer high information gain at lower cost. Empirical evaluations on CIFAR-10, CIFAR-100, and ImageNet64x64 demonstrate the effectiveness and scalability of our framework. Notably, it reduces labeling cost by 48% on ImageNet64x64. The project page can be found at https://yehogwon.github.io/csq-al.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 41 of its 77 references that are in the map. First posted on arXiv 10 Feb 2025.
Builds on
41 of 77 references.
References · 41
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2023GPT-4 Technical Reportcited by 18,132
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2023Segment Anythingcited by 8,158
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2016Wide Residual Networkscited by 3,057
- 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
- 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
29 more
- 2021Scaling Vision Transformerscited by 993
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
- 2017Deep Learning Scaling is Predictable, Empiricallycited by 556
- 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
- 2020Classification with Valid and Adaptive Coveragecited by 390
- 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 374
- 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 365
- 2019Variational Adversarial Active Learningcited by 284
- 2019NLNL: Negative Learning for Noisy Labelscited by 151
- 2022Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)cited by 137
- 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
- 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
- 2018Generative Adversarial Active Learning for Unsupervised Outlier Detectioncited by 65
- 2022Active Learning Through a Covering Lenscited by 62
- 2019Bayesian Generative Active Deep Learningcited by 57
- 2023AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weekscited by 52
- 2020Products-10K: A Large-scale Product Recognition Datasetcited by 42
- 2017Active Learning for Cost-Sensitive Classificationcited by 40
- 2022Active Learning for Open-set Annotationcited by 33
- 2022Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learningcited by 24
- 2023LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learningcited by 20
- 2021A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classificationcited by 17
- 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 16
- 2022Combating Label Distribution Shift for Active Domain Adaptationcited by 14
- 2024Uncertainty for Active Learning on Graphscited by 11
- 2020One-bit Supervision for Image Classificationcited by 10
- 2023Active Learning for Semantic Segmentation with Multi-class Label Querycited by 9
- 2024Querying Easily Flip-flopped Samples for Deep Active Learningcited by 7
- 2024Active Label Correction for Semantic Segmentation with Foundation Modelscited by 7
Built on by
Citing papers per year: 2026: 3.
3 papers.