# NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination

arXiv: https://arxiv.org/abs/2007.13376 · HTML: https://mlsanity.com/paper/2007.13376/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision](https://mlsanity.com/paper/2304.03135/) (2023)
- [Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models](https://mlsanity.com/paper/2405.04180/) (2024)
- [V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection](https://mlsanity.com/paper/2104.03106/) (2021)
- [Pedestrian Detection by Exemplar-Guided Contrastive Learning](https://mlsanity.com/paper/2111.08974/) (2021)
- [Accelerating Non-Maximum Suppression: A Graph Theory Perspective](https://mlsanity.com/paper/2409.20520/) (2024)
- [Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibration](https://mlsanity.com/paper/2309.03110/) (2023)
- [Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection](https://mlsanity.com/paper/2511.10308/) (2025)
- [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)

## Abstract (arXiv)

Greedy-NMS inherently raises a dilemma, where a lower NMS threshold will potentially lead to a lower recall rate and a higher threshold introduces more false positives. This problem is more severe in pedestrian detection because the instance density varies more intensively. However, previous works on NMS don't consider or vaguely consider the factor of the existent of nearby pedestrians. Thus, we propose Nearby Objects Hallucinator (NOH), which pinpoints the objects nearby each proposal with a Gaussian distribution, together with NOH-NMS, which dynamically eases the suppression for the space that might contain other objects with a high likelihood. Compared to Greedy-NMS, our method, as the state-of-the-art, improves by 3.9% AP, 5.1% Recall, and 0.8% MR-2 on CrowdHuman to 89.0% AP and 92.9% Recall, and 43.9% MR-2 respectively.