# Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond

arXiv: https://arxiv.org/abs/2201.03176 · HTML: https://mlsanity.com/paper/2201.03176/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 56 references that are in the map.
- First posted on arXiv 10 Jan 2022.

## Builds on (most cited first, 30 of 35)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://mlsanity.com/paper/1805.00123/) (2018)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/1901.08211/) (2019)
- [A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection](https://mlsanity.com/paper/1607.07155/) (2016)
- [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)
- [Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd](https://mlsanity.com/paper/1807.08407/) (2018)
- [The EuroCity Persons Dataset: A Novel Benchmark for Object Detection](https://mlsanity.com/paper/1805.07193/) (2018)
- [WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild](https://mlsanity.com/paper/1909.12118/) (2019)
- [Is Faster R-CNN Doing Well for Pedestrian Detection?](https://mlsanity.com/paper/1607.07032/) (2016)
- [Mask-Guided Attention Network for Occluded Pedestrian Detection](https://mlsanity.com/paper/1910.06160/) (2019)
- [How Far are We from Solving Pedestrian Detection?](https://mlsanity.com/paper/1602.01237/) (2016)
- [What Can Help Pedestrian Detection?](https://mlsanity.com/paper/1705.02757/) (2017)
- [Illuminating Pedestrians via Simultaneous Detection & Segmentation](https://mlsanity.com/paper/1706.08564/) (2017)
- [Attribute-aware Pedestrian Detection in a Crowd](https://mlsanity.com/paper/1910.09188/) (2019)
- [Learning Complexity-Aware Cascades for Deep Pedestrian Detection](https://mlsanity.com/paper/1507.05348/) (2015)
- [FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction](https://mlsanity.com/paper/1901.03495/) (2019)

## Built on by (most cited first, 8 of 8)

- [Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks](https://mlsanity.com/paper/2303.17602/) (2023)
- [Uncertainty estimation for Cross-dataset performance in Trajectory prediction](https://mlsanity.com/paper/2205.07310/) (2022)
- [Vision transformers in domain adaptation and domain generalization: a study of robustness](https://mlsanity.com/paper/2404.04452/) (2024)
- [Bias Behind the Wheel: Fairness Testing of Autonomous Driving Systems](https://mlsanity.com/paper/2308.02935/) (2023)
- [Ambiguous Annotations: When is a Pedestrian not a Pedestrian?](https://mlsanity.com/paper/2405.08794/) (2024)
- [How Does Traffic Environment Quantitatively Affect the Autonomous Driving Prediction?](https://mlsanity.com/paper/2301.04414/) (2023)
- [Open-source data pipeline for street-view images: a case study on community mobility during COVID-19 pandemic](https://mlsanity.com/paper/2401.13087/) (2024)
- [MASH-Bench: Diagnosing Cross-Source Failure in Mass-Shooting Risk Classification](https://mlsanity.com/paper/2608.22460/) (2026)

## Abstract (arXiv)

Pedestrian detection is the cornerstone of many vision based applications, starting from object tracking to video surveillance and more recently, autonomous driving. With the rapid development of deep learning in object detection, pedestrian detection has achieved very good performance in traditional single-dataset training and evaluation setting. However, in this study on generalizable pedestrian detectors, we show that, current pedestrian detectors poorly handle even small domain shifts in cross-dataset evaluation. We attribute the limited generalization to two main factors, the method and the current sources of data. Regarding the method, we illustrate that biasness present in the design choices (e.g anchor settings) of current pedestrian detectors are the main contributing factor to the limited generalization. Most modern pedestrian detectors are tailored towards target dataset, where they do achieve high performance in traditional single training and testing pipeline, but suffer a degrade in performance when evaluated through cross-dataset evaluation. Consequently, a general object detector performs better in cross-dataset evaluation compared with state of the art pedestrian detectors, due to its generic design. As for the data, we show that the autonomous driving benchmarks are monotonous in nature, that is, they are not diverse in scenarios and dense in pedestrians. Therefore, benchmarks curated by crawling the web (which contain diverse and dense scenarios), are an efficient source of pre-training for providing a more robust representation. Accordingly, we propose a progressive fine-tuning strategy which improves generalization. Code and models can accessed at https://github.com/hasanirtiza/Pedestron.