# Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors

arXiv: https://arxiv.org/abs/2309.08771 · HTML: https://mlsanity.com/paper/2309.08771/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 73 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Harmonizing Transferability and Discriminability for Adapting Object Detectors](https://mlsanity.com/paper/2003.06297/) (2020)
- [Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector](https://mlsanity.com/paper/2008.08574/) (2020)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection](https://mlsanity.com/paper/1909.00597/) (2019)
- [Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection](https://mlsanity.com/paper/2110.01428/) (2021)
- [Anchor-Free Person Search](https://mlsanity.com/paper/2103.11617/) (2021)
- [How Far are We from Solving Pedestrian Detection?](https://mlsanity.com/paper/1602.01237/) (2016)
- [I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors](https://mlsanity.com/paper/2103.13757/) (2021)
- [Domain-Specific Suppression for Adaptive Object Detection](https://mlsanity.com/paper/2105.03570/) (2021)

## Built on by (most cited first, 5 of 5)

- [BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictions](https://mlsanity.com/paper/2312.13514/) (2023)
- [Do computer vision foundation models learn the low-level characteristics of the human visual system?](https://mlsanity.com/paper/2502.20256/) (2025)
- [MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors](https://mlsanity.com/paper/2602.05330/) (2026)
- [Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions](https://mlsanity.com/paper/2411.18823/) (2024)
- [Break Stylistic Sophon: Are We Really Meant to Confine the Imagination in Style Transfer?](https://mlsanity.com/paper/2506.15033/) (2025)

## Abstract (arXiv)

Cross-domain pedestrian detection aims to generalize pedestrian detectors from one label-rich domain to another label-scarce domain, which is crucial for various real-world applications. Most recent works focus on domain alignment to train domain-adaptive detectors either at the instance level or image level. From a practical point of view, one-stage detectors are faster. Therefore, we concentrate on designing a cross-domain algorithm for rapid one-stage detectors that lacks instance-level proposals and can only perform image-level feature alignment. However, pure image-level feature alignment causes the foreground-background misalignment issue to arise, i.e., the foreground features in the source domain image are falsely aligned with background features in the target domain image. To address this issue, we systematically analyze the importance of foreground and background in image-level cross-domain alignment, and learn that background plays a more critical role in image-level cross-domain alignment. Therefore, we focus on cross-domain background feature alignment while minimizing the influence of foreground features on the cross-domain alignment stage. This paper proposes a novel framework, namely, background-focused distribution alignment (BFDA), to train domain adaptive onestage pedestrian detectors. Specifically, BFDA first decouples the background features from the whole image feature maps and then aligns them via a novel long-short-range discriminator.