# Progressive End-to-End Object Detection in Crowded Scenes

arXiv: https://arxiv.org/abs/2203.07669 · HTML: https://mlsanity.com/paper/2203.07669/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 55 references that are in the map.
- First posted on arXiv 15 Mar 2022.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://mlsanity.com/paper/1805.00123/) (2018)
- [Fast Convergence of DETR with Spatially Modulated Co-Attention](https://mlsanity.com/paper/2101.07448/) (2021)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [FCOS: A simple and strong anchor-free object detector](https://mlsanity.com/paper/2006.09214/) (2020)
- [Rethinking Transformer-based Set Prediction for Object Detection](https://mlsanity.com/paper/2011.10881/) (2020)
- [End-to-end people detection in crowded scenes](https://mlsanity.com/paper/1506.04878/) (2015)
- [Single-Shot Refinement Neural Network for Object Detection](https://mlsanity.com/paper/1711.06897/) (2017)
- [TIDE: A General Toolbox for Identifying Object Detection Errors](https://mlsanity.com/paper/2008.08115/) (2020)
- [Learning non-maximum suppression](https://mlsanity.com/paper/1705.02950/) (2017)
- [End-to-End Object Detection with Adaptive Clustering Transformer](https://mlsanity.com/paper/2011.09315/) (2020)
- [End-to-End Object Detection with Fully Convolutional Network](https://mlsanity.com/paper/2012.03544/) (2020)
- [Adaptive NMS: Refining Pedestrian Detection in a Crowd](https://mlsanity.com/paper/1904.03629/) (2019)
- [Repulsion Loss: Detecting Pedestrians in a Crowd](https://mlsanity.com/paper/1711.07752/) (2017)
- [Detection in Crowded Scenes: One Proposal, Multiple Predictions](https://mlsanity.com/paper/2003.09163/) (2020)
- [Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd](https://mlsanity.com/paper/1807.08407/) (2018)
- [NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing](https://mlsanity.com/paper/2003.12729/) (2020)

## Built on by (most cited first, 30 of 31)

- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [UniHCP: A Unified Model for Human-Centric Perceptions](https://mlsanity.com/paper/2303.02936/) (2023)
- [HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining](https://mlsanity.com/paper/2303.05675/) (2023)
- [Hulk: A Universal Knowledge Translator for Human-Centric Tasks](https://mlsanity.com/paper/2312.01697/) (2023)
- [VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision](https://mlsanity.com/paper/2304.03135/) (2023)
- [Reconstructing Groups of People with Hypergraph Relational Reasoning](https://mlsanity.com/paper/2308.15844/) (2023)
- [Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes](https://mlsanity.com/paper/2407.11464/) (2024)
- [Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection](https://mlsanity.com/paper/2311.01025/) (2023)
- [When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset](https://mlsanity.com/paper/2407.10125/) (2024)
- [You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception](https://mlsanity.com/paper/2312.05525/) (2023)
- [RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation](https://mlsanity.com/paper/2411.13150/) (2024)
- [Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes](https://mlsanity.com/paper/2503.13739/) (2025)
- [Improving Crowded Object Detection via Copy-Paste](https://mlsanity.com/paper/2211.12110/) (2022)
- [DEYO: DETR with YOLO for End-to-End Object Detection](https://mlsanity.com/paper/2402.16370/) (2024)
- [ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection](https://mlsanity.com/paper/2309.08196/) (2023)
- [Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection](https://mlsanity.com/paper/2305.10801/) (2023)
- [RecursiveDet: End-to-End Region-based Recursive Object Detection](https://mlsanity.com/paper/2307.13619/) (2023)
- [Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bank](https://mlsanity.com/paper/2404.19299/) (2024)
- [Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems](https://mlsanity.com/paper/2209.10058/) (2022)
- [BPJDet: Extended Object Representation for Generic Body-Part Joint Detection](https://mlsanity.com/paper/2304.10765/) (2023)
- [PBADet: A One-Stage Anchor-Free Approach for Part-Body Association](https://mlsanity.com/paper/2402.07814/) (2024)
- [Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion](https://mlsanity.com/paper/2405.01311/) (2024)
- [CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes](https://mlsanity.com/paper/2509.08738/) (2025)
- [Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems](https://mlsanity.com/paper/2210.01000/) (2022)
- [TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection](https://mlsanity.com/paper/2211.00826/) (2022)
- [Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems](https://mlsanity.com/paper/2211.12685/) (2022)
- [DINF: Dynamic Instance Noise Filter for Occluded Pedestrian Detection](https://mlsanity.com/paper/2301.05565/) (2023)
- [Ranking-based Adaptive Query Generation for DETRs in Crowded Pedestrian Detection](https://mlsanity.com/paper/2310.15725/) (2023)
- [Dense Object Detection Based on De-homogenized Queries](https://mlsanity.com/paper/2502.07194/) (2025)
- [Zero-Shot Multi-Animal Tracking in the Wild](https://mlsanity.com/paper/2511.02591/) (2025)

## Abstract (arXiv)

In this paper, we propose a new query-based detection framework for crowd detection. Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. Benefiting from the nature of the one-to-one label assignment rule, we propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries prone to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes. Equipped with our approach, Sparse RCNN achieves 92.0% AP, 41.4% MR-2 and 83.2% JI on the challenging CrowdHuman citeshao2018crowdhuman dataset, outperforming the box-based method MIP citechu2020detection that specifies in handling crowded scenarios. Moreover, the proposed method, robust to crowdedness, can still obtain consistent improvements on moderately and slightly crowded datasets like CityPersons citezhang2017citypersons and COCO citelin2014microsoft. Code will be made publicly available at https://github.com/megvii-model/Iter-E2EDET.