# Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection

arXiv: https://arxiv.org/abs/2503.16125 · HTML: https://mlsanity.com/paper/2503.16125/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 72 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 30 of 43)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Contextual Diversity for Active Learning](https://mlsanity.com/paper/2008.05723/) (2020)
- [Batch Active Learning at Scale](https://mlsanity.com/paper/2107.14263/) (2021)
- [Infinite Mixture Prototypes for Few-Shot Learning](https://mlsanity.com/paper/1902.04552/) (2019)
- [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019)
- [Improved Analysis of Clipping Algorithms for Non-convex Optimization](https://mlsanity.com/paper/2010.02519/) (2020)
- [Influence Selection for Active Learning](https://mlsanity.com/paper/2108.09331/) (2021)
- [MLCVNet: Multi-Level Context VoteNet for 3D Object Detection](https://mlsanity.com/paper/2004.05679/) (2020)
- [Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2006.12052/) (2020)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Generative Sparse Detection Networks for 3D Single-shot Object Detection](https://mlsanity.com/paper/2006.12356/) (2020)
- [Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint](https://mlsanity.com/paper/2204.07965/) (2022)
- [ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2107.11769/) (2021)
- [Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector](https://mlsanity.com/paper/1901.10609/) (2019)
- [Active Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.08348/) (2023)
- [V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection](https://mlsanity.com/paper/2308.04409/) (2023)
- [Plug and Play Active Learning for Object Detection](https://mlsanity.com/paper/2211.11612/) (2022)
- [Exploring Active 3D Object Detection from a Generalization Perspective](https://mlsanity.com/paper/2301.09249/) (2023)
- [Rethinking IoU-based Optimization for Single-stage 3D Object Detection](https://mlsanity.com/paper/2207.09332/) (2022)

## Built on by (most cited first, 7 of 7)

- [CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2603.23276/) (2026)
- [Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments](https://mlsanity.com/paper/2604.07997/) (2026)
- [Conformal Cross-Modal Active Learning](https://mlsanity.com/paper/2603.23159/) (2026)
- [Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection](https://mlsanity.com/paper/2607.14560/) (2026)
- [Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training](https://mlsanity.com/paper/2608.19973/) (2026)
- [FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection](https://mlsanity.com/paper/2609.02212/) (2026)
- [Distance to Class Prototypes: Active Learning for Object Detection](https://mlsanity.com/paper/2609.20248/) (2026)

## Abstract (arXiv)

Active learning has emerged as a promising approach to reduce the substantial annotation burden in 3D object detection tasks, spurring several initiatives in outdoor environments. However, its application in indoor environments remains unexplored. Compared to outdoor 3D datasets, indoor datasets face significant challenges, including fewer training samples per class, a greater number of classes, more severe class imbalance, and more diverse scene types and intra-class variances. This paper presents the first study on active learning for indoor 3D object detection, where we propose a novel framework tailored for this task. Our method incorporates two key criteria - uncertainty and diversity - to actively select the most ambiguous and informative unlabeled samples for annotation. The uncertainty criterion accounts for both inaccurate detections and undetected objects, ensuring that the most ambiguous samples are prioritized. Meanwhile, the diversity criterion is formulated as a joint optimization problem that maximizes the diversity of both object class distributions and scene types, using a new Class-aware Adaptive Prototype (CAP) bank. The CAP bank dynamically allocates representative prototypes to each class, helping to capture varying intra-class diversity across different categories. We evaluate our method on SUN RGB-D and ScanNetV2, where it outperforms baselines by a significant margin, achieving over 85% of fully-supervised performance with just 10% of the annotation budget.