# Enhancing Cost Efficiency in Active Learning with Candidate Set Query

arXiv: https://arxiv.org/abs/2502.06209 · HTML: https://mlsanity.com/paper/2502.06209/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 77 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Deep Learning Scaling is Predictable, Empirically](https://mlsanity.com/paper/1712.00409/) (2017)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [Uncertainty Sets for Image Classifiers using Conformal Prediction](https://mlsanity.com/paper/2009.14193/) (2020)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [NLNL: Negative Learning for Noisy Labels](https://mlsanity.com/paper/1908.07387/) (2019)
- [Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)](https://mlsanity.com/paper/2205.01397/) (2022)
- [Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets](https://mlsanity.com/paper/2202.02794/) (2022)
- [SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios](https://mlsanity.com/paper/2107.00717/) (2021)
- [Active Learning Through a Covering Lens](https://mlsanity.com/paper/2205.11320/) (2022)
- [Generative Adversarial Active Learning for Unsupervised Outlier Detection](https://mlsanity.com/paper/1809.10816/) (2018)
- [Bayesian Generative Active Deep Learning](https://mlsanity.com/paper/1904.11643/) (2019)
- [AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks](https://mlsanity.com/paper/2305.09666/) (2023)
- [Products-10K: A Large-scale Product Recognition Dataset](https://mlsanity.com/paper/2008.10545/) (2020)
- [Active Learning for Cost-Sensitive Classification](https://mlsanity.com/paper/1703.01014/) (2017)

## Built on by (most cited first, 3 of 3)

- [Conformal Cross-Modal Active Learning](https://mlsanity.com/paper/2603.23159/) (2026)
- [IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning](https://mlsanity.com/paper/2605.01668/) (2026)
- [Cost-efficient Active Learning for Referring Image Segmentation and Grounding](https://mlsanity.com/paper/2608.30621/) (2026)

## 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.