# Box-Level Active Detection

arXiv: https://arxiv.org/abs/2303.13089 · HTML: https://mlsanity.com/paper/2303.13089/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Builds on (most cited first, 30 of 32)

- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Contextual Diversity for Active Learning](https://mlsanity.com/paper/2008.05723/) (2020)
- [Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost](https://mlsanity.com/paper/1910.07153/) (2019)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Towards Robust and Reproducible Active Learning Using Neural Networks](https://mlsanity.com/paper/2002.09564/) (2020)
- [Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint](https://mlsanity.com/paper/2204.07965/) (2022)
- [Localization-Aware Active Learning for Object Detection](https://mlsanity.com/paper/1801.05124/) (2018)
- [Active Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.08348/) (2023)
- [Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection](https://mlsanity.com/paper/2012.01950/) (2020)
- [Solving Missing-Annotation Object Detection with Background Recalibration Loss](https://mlsanity.com/paper/2002.05274/) (2020)
- [Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection](https://mlsanity.com/paper/2106.11921/) (2021)
- [Soft Sampling for Robust Object Detection](https://mlsanity.com/paper/1806.06986/) (2018)
- [An Adaptive Supervision Framework for Active Learning in Object Detection](https://mlsanity.com/paper/1908.02454/) (2019)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects](https://mlsanity.com/paper/1811.10862/) (2018)
- [SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining](https://mlsanity.com/paper/2201.04620/) (2022)
- [BAOD: Budget-Aware Object Detection](https://mlsanity.com/paper/1904.05443/) (2019)

## Built on by (most cited first, 13 of 13)

- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving](https://mlsanity.com/paper/2403.17373/) (2024)
- [PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation](https://mlsanity.com/paper/2403.09192/) (2024)
- [Zero-Shot Coreset Selection via Iterative Subspace Sampling](https://mlsanity.com/paper/2411.15349/) (2024)
- [YOLO-UniOW: Efficient Universal Open-World Object Detection](https://mlsanity.com/paper/2412.20645/) (2024)
- [Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence](https://mlsanity.com/paper/2407.18899/) (2024)
- [Quantized Prompt for Efficient Generalization of Vision-Language Models](https://mlsanity.com/paper/2407.10704/) (2024)
- [ActiveDC: Distribution Calibration for Active Finetuning](https://mlsanity.com/paper/2311.07634/) (2023)
- [IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection](https://mlsanity.com/paper/2511.19301/) (2025)
- [Performance-guided Reinforced Active Learning for Object Detection](https://mlsanity.com/paper/2601.15688/) (2026)
- [Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning](https://mlsanity.com/paper/2503.13383/) (2025)
- [Box-Level Class-Balanced Sampling for Active Object Detection](https://mlsanity.com/paper/2508.17849/) (2025)
- [BMD-45: A Large-Scale CCTV Vehicle Detection Dataset for Urban Traffic in Developing Cities](https://mlsanity.com/paper/2604.24419/) (2026)

## Abstract (arXiv)

Active learning selects informative samples for annotation within budget, which has proven efficient recently on object detection. However, the widely used active detection benchmarks conduct image-level evaluation, which is unrealistic in human workload estimation and biased towards crowded images. Furthermore, existing methods still perform image-level annotation, but equally scoring all targets within the same image incurs waste of budget and redundant labels. Having revealed above problems and limitations, we introduce a box-level active detection framework that controls a box-based budget per cycle, prioritizes informative targets and avoids redundancy for fair comparison and efficient application. Under the proposed box-level setting, we devise a novel pipeline, namely Complementary Pseudo Active Strategy (ComPAS). It exploits both human annotations and the model intelligence in a complementary fashion: an efficient input-end committee queries labels for informative objects only; meantime well-learned targets are identified by the model and compensated with pseudo-labels. ComPAS consistently outperforms 10 competitors under 4 settings in a unified codebase. With supervision from labeled data only, it achieves 100% supervised performance of VOC0712 with merely 19% box annotations. On the COCO dataset, it yields up to 4.3% mAP improvement over the second-best method. ComPAS also supports training with the unlabeled pool, where it surpasses 90% COCO supervised performance with 85% label reduction. Our source code is publicly available at https://github.com/lyumengyao/blad.