# IterDet: Iterative Scheme for Object Detection in Crowded Environments

arXiv: https://arxiv.org/abs/2005.05708 · HTML: https://mlsanity.com/paper/2005.05708/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2020.

## Built on by (most cited first, 12 of 12)

- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [Towards Domain Generalization in Object Detection](https://mlsanity.com/paper/2203.14387/) (2022)
- [CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement](https://mlsanity.com/paper/2103.07017/) (2021)
- [Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bank](https://mlsanity.com/paper/2404.19299/) (2024)
- [Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle](https://mlsanity.com/paper/2412.01562/) (2024)
- [Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection](https://mlsanity.com/paper/2505.21868/) (2025)
- [DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection](https://mlsanity.com/paper/2507.19807/) (2025)
- [SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds](https://mlsanity.com/paper/2601.08982/) (2026)
- [TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection](https://mlsanity.com/paper/2211.00826/) (2022)
- [DINF: Dynamic Instance Noise Filter for Occluded Pedestrian Detection](https://mlsanity.com/paper/2301.05565/) (2023)
- [BBoxMaskPose v2: Expanding Mutual Conditioning to 3D](https://mlsanity.com/paper/2601.15200/) (2026)
- [Boundary and Position Information Mining for Aerial Small Object Detection](https://mlsanity.com/paper/2601.16617/) (2026)

## Abstract (arXiv)

Deep learning-based detectors usually produce a redundant set of object bounding boxes including many duplicate detections of the same object. These boxes are then filtered using non-maximum suppression (NMS) in order to select exactly one bounding box per object of interest. This greedy scheme is simple and provides sufficient accuracy for isolated objects but often fails in crowded environments, since one needs to both preserve boxes for different objects and suppress duplicate detections. In this work we develop an alternative iterative scheme, where a new subset of objects is detected at each iteration. Detected boxes from the previous iterations are passed to the network at the following iterations to ensure that the same object would not be detected twice. This iterative scheme can be applied to both one-stage and two-stage object detectors with just minor modifications of the training and inference procedures. We perform extensive experiments with two different baseline detectors on four datasets and show significant improvement over the baseline, leading to state-of-the-art performance on CrowdHuman and WiderPerson datasets. The source code and the trained models are available at https://github.com/saic-vul/iterdet.