# Contextual Diversity for Active Learning

arXiv: https://arxiv.org/abs/2008.05723 · HTML: https://mlsanity.com/paper/2008.05723/

## Key facts

- Cited by 139 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2020.

## Built on by (most cited first, 30 of 139)

- [DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning](https://mlsanity.com/paper/2204.08499/) (2022)
- [InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning](https://mlsanity.com/paper/2303.04947/) (2023)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Active Learning by Feature Mixing](https://mlsanity.com/paper/2203.07034/) (2022)
- [Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint](https://mlsanity.com/paper/2204.07965/) (2022)
- [Dataset Quantization](https://mlsanity.com/paper/2308.10524/) (2023)
- [Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm](https://mlsanity.com/paper/2303.14382/) (2023)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Loss-Curvature Matching for Dataset Selection and Condensation](https://mlsanity.com/paper/2303.04449/) (2023)
- [Active Generalized Category Discovery](https://mlsanity.com/paper/2403.04272/) (2024)
- [Active learning for data streams: a survey](https://mlsanity.com/paper/2302.08893/) (2023)
- [The Trickle-down Impact of Reward (In-)consistency on RLHF](https://mlsanity.com/paper/2309.16155/) (2023)
- [Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models](https://mlsanity.com/paper/2408.02085/) (2024)
- [Plug and Play Active Learning for Object Detection](https://mlsanity.com/paper/2211.11612/) (2022)
- [A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances](https://mlsanity.com/paper/2505.17799/) (2025)
- [Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection](https://mlsanity.com/paper/2106.11921/) (2021)
- [In Defense of Core-set: A Density-aware Core-set Selection for Active Learning](https://mlsanity.com/paper/2206.04838/) (2022)
- [Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment](https://mlsanity.com/paper/2301.10625/) (2023)
- [Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning](https://mlsanity.com/paper/2305.18424/) (2023)
- [Making Your First Choice: To Address Cold Start Problem in Vision Active Learning](https://mlsanity.com/paper/2210.02442/) (2022)
- [SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning](https://mlsanity.com/paper/2405.00705/) (2024)
- [From Selection to Generation: A Survey of LLM-based Active Learning](https://mlsanity.com/paper/2502.11767/) (2025)
- [MCDAL: Maximum Classifier Discrepancy for Active Learning](https://mlsanity.com/paper/2107.11049/) (2021)
- [Learning Distinctive Margin toward Active Domain Adaptation](https://mlsanity.com/paper/2203.05738/) (2022)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [DOS: Diverse Outlier Sampling for Out-of-Distribution Detection](https://mlsanity.com/paper/2306.02031/) (2023)
- [ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving](https://mlsanity.com/paper/2403.02877/) (2024)
- [Active Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2207.11493/) (2022)
- [A Short Survey on Importance Weighting for Machine Learning](https://mlsanity.com/paper/2403.10175/) (2024)
- [ESA: Annotation-Efficient Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2408.13491/) (2024)

## Abstract (arXiv)

Requirement of large annotated datasets restrict the use of deep convolutional neural networks (CNNs) for many practical applications. The problem can be mitigated by using active learning (AL) techniques which, under a given annotation budget, allow to select a subset of data that yields maximum accuracy upon fine tuning. State of the art AL approaches typically rely on measures of visual diversity or prediction uncertainty, which are unable to effectively capture the variations in spatial context. On the other hand, modern CNN architectures make heavy use of spatial context for achieving highly accurate predictions. Since the context is difficult to evaluate in the absence of ground-truth labels, we introduce the notion of contextual diversity that captures the confusion associated with spatially co-occurring classes. Contextual Diversity (CD) hinges on a crucial observation that the probability vector predicted by a CNN for a region of interest typically contains information from a larger receptive field. Exploiting this observation, we use the proposed CD measure within two AL frameworks: (1) a core-set based strategy and (2) a reinforcement learning based policy, for active frame selection. Our extensive empirical evaluation establish state of the art results for active learning on benchmark datasets of Semantic Segmentation, Object Detection and Image Classification. Our ablation studies show clear advantages of using contextual diversity for active learning. The source code and additional results are available at https://github.com/sharat29ag/CDAL.