# Consistency-based Active Learning for Object Detection

arXiv: https://arxiv.org/abs/2103.10374 · HTML: https://mlsanity.com/paper/2103.10374/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 57 references that are in the map.
- First posted on arXiv 18 Mar 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [DetCo: Unsupervised Contrastive Learning for Object Detection](https://mlsanity.com/paper/2102.04803/) (2021)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [Learning Data Augmentation Strategies for Object Detection](https://mlsanity.com/paper/1906.11172/) (2019)
- [Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost](https://mlsanity.com/paper/1910.07153/) (2019)

## Built on by (most cited first, 30 of 32)

- [CitySim: A Drone-Based Vehicle Trajectory Dataset for Safety Oriented Research and Digital Twins](https://mlsanity.com/paper/2208.11036/) (2022)
- [Active Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.08348/) (2023)
- [Plug and Play Active Learning for Object Detection](https://mlsanity.com/paper/2211.11612/) (2022)
- [Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2205.07708/) (2022)
- [KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection](https://mlsanity.com/paper/2307.07942/) (2023)
- [Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning](https://mlsanity.com/paper/2307.08415/) (2023)
- [Multi-Task Consistency for Active Learning](https://mlsanity.com/paper/2306.12398/) (2023)
- [ALBench: A Framework for Evaluating Active Learning in Object Detection](https://mlsanity.com/paper/2207.13339/) (2022)
- [Deep Active Learning for Computer Vision: Past and Future](https://mlsanity.com/paper/2211.14819/) (2022)
- [ACTRESS: Active Retraining for Semi-supervised Visual Grounding](https://mlsanity.com/paper/2407.03251/) (2024)
- [Active Learning for Object Detection with Non-Redundant Informative Sampling](https://mlsanity.com/paper/2307.08414/) (2023)
- [Assessing Domain Gap for Continual Domain Adaptation in Object Detection](https://mlsanity.com/paper/2302.10396/) (2023)
- [Streamlining the Development of Active Learning Methods in Real-World Object Detection](https://mlsanity.com/paper/2508.19906/) (2025)
- [Query-based Hard-Image Retrieval for Object Detection at Test Time](https://mlsanity.com/paper/2209.11559/) (2022)
- [Boosting Semi-Supervised Object Detection in Remote Sensing Images With Active Teaching](https://mlsanity.com/paper/2402.18958/) (2024)
- [3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation](https://mlsanity.com/paper/2504.12599/) (2025)
- [Fair Robust Active Learning by Joint Inconsistency](https://mlsanity.com/paper/2209.10729/) (2022)
- [Evaluating Zero-cost Active Learning for Object Detection](https://mlsanity.com/paper/2212.04211/) (2022)
- [Benchmarking of Query Strategies: Towards Future Deep Active Learning](https://mlsanity.com/paper/2312.05751/) (2023)
- [Table Detection with Active Learning](https://mlsanity.com/paper/2509.20003/) (2025)
- [Semi-Automated Construction of Food Composition Knowledge Base](https://mlsanity.com/paper/2301.11322/) (2023)
- [MuRAL: Multi-Scale Region-based Active Learning for Object Detection](https://mlsanity.com/paper/2303.16637/) (2023)
- [HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detection](https://mlsanity.com/paper/2505.00507/) (2025)
- [Box-Level Class-Balanced Sampling for Active Object Detection](https://mlsanity.com/paper/2508.17849/) (2025)
- [Cumulative Consensus Score: Label-Free and Model-Agnostic Evaluation of Object Detectors in Deployment](https://mlsanity.com/paper/2509.12871/) (2025)
- [Learnability-Driven Submodular Optimization for Active Roadside 3D Detection](https://mlsanity.com/paper/2601.01695/) (2026)
- [Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images](https://mlsanity.com/paper/2602.05250/) (2026)
- [HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration](https://mlsanity.com/paper/2606.28215/) (2026)
- [Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection](https://mlsanity.com/paper/2607.15974/) (2026)
- [Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Tracking](https://mlsanity.com/paper/2608.17224/) (2026)

## Abstract (arXiv)

Active learning aims to improve the performance of task model by selecting the most informative samples with a limited budget. Unlike most recent works that focused on applying active learning for image classification, we propose an effective Consistency-based Active Learning method for object Detection (CALD), which fully explores the consistency between original and augmented data. CALD has three appealing benefits. (i) CALD is systematically designed by investigating the weaknesses of existing active learning methods, which do not take the unique challenges of object detection into account. (ii) CALD unifies box regression and classification with a single metric, which is not concerned by active learning methods for classification. CALD also focuses on the most informative local region rather than the whole image, which is beneficial for object detection. (iii) CALD not only gauges individual information for sample selection, but also leverages mutual information to encourage a balanced data distribution. Extensive experiments show that CALD significantly outperforms existing state-of-the-art task-agnostic and detection-specific active learning methods on general object detection datasets. Based on the Faster R-CNN detector, CALD consistently surpasses the baseline method (random selection) by 2.9/2.8/0.8 mAP on average on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO. Code is available at urlhttps://github.com/we1pingyu/CALD