Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors
- 25 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 4935-4950
Abstract
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 one-stage 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. Extensive experiments demonstrate that compared to mainstream domain adaptation technologies, BFDA significantly enhances cross-domain pedestrian detection performance for either one-stage or two-stage detectors. Moreover, by employing the efficient one-stage detector (YOLOv5), BFDA can reach 217.4 FPS (640×480 pixels) on NVIDIA Tesla V100 (7~12 times the FPS of the existing frameworks), which is highly significant for practical applications. The code from this study will be made publicly available.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62071127, U1909207)
- Shanghai Natural Science Foundation (23ZR1402900)
- Zhejiang Laboratory (2021KH0AB05)
This publication has 59 references indexed in Scilit:
- Unsupervised Deep Domain Adaptation for Pedestrian Detection2016
- SSD: Single Shot MultiBox Detector2016
- GPU-based Pedestrian Detection for Autonomous DrivingProcedia Computer Science, 2016
- Learning scene-specific pedestrian detectors without real data2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Pedestrian Detection: An Evaluation of the State of the ArtIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- A theory of learning from different domainsMachine Learning, 2009
- Direct importance estimation for covariate shift adaptationAnnals of the Institute of Statistical Mathematics, 2008
- Robust Tracking Using Foreground-Background Texture DiscriminationInternational Journal of Computer Vision, 2006
- Improving performance of distribution tracking through background mismatchIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005