EUVIMEDEUVIMED entdecken
Crossref

Robust Domain Adaptive Object Detection With Unified Multi-Granularity Alignment

Libo Zhang, Wenzhang Zhou, Heng Fan, Tiejian Luo, Haibin Ling

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 9161-9178

DOI: 10.1109/tpami.2024.3416098 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Libo Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 91 Literaturangaben. Gefördert von: Chinese Academy of Medical Sciences (CAMS) Innovation Fund for Medical Sciences, Youth Innovation Promotion Association, CAS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Domain adaptive detection aims to improve the generalization of detectors on target domain. To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning. However, they neglect the relationship between multiple granularities and different features in alignment, degrading detection. Addressing this, we introduce a unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning. The key is to encode the dependencies across different granularities including pixel-, instance-, and category-levels simultaneously to align two domains. Specifically, based on pixel-level features, we first develop an omni-scale gated fusion (OSGF) module to aggregate discriminative representations of instances with scale-aware convolutions, leading to robust multi-scale detection. Besides, we introduce multi-granularity discriminators to identify where, either source or target domains, different granularities of samples come from. Note that, MGA not only leverages instance discriminability in different categories but also exploits category consistency between two domains for detection. Furthermore, we present an adaptive exponential moving average (AEMA) strategy that explores model assessments for model update to improve pseudo labels and alleviate local misalignment problem, boosting detection robustness. Extensive experiments on multiple domain adaption scenarios validate the superiority of MGA over other approaches on FCOS and Faster R-CNN detectors.

Förderung

  • Chinese Academy of Medical Sciences (CAMS) Innovation Fund for Medical Sciences
  • Youth Innovation Promotion Association
  • CAS

Zitieren

APA

Zhang, L., Zhou, W., Fan, H., Luo, T., & Ling, H. (2024). Robust Domain Adaptive Object Detection With Unified Multi-Granularity Alignment. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9161-9178. https://doi.org/10.1109/tpami.2024.3416098

Vancouver

Zhang L, Zhou W, Fan H, Luo T, Ling H. Robust Domain Adaptive Object Detection With Unified Multi-Granularity Alignment. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):9161-9178. doi:10.1109/tpami.2024.3416098

BibTeX
@article{Zhang2024,
  author = {Zhang, Libo and Zhou, Wenzhang and Fan, Heng and Luo, Tiejian and Ling, Haibin},
  title = {Robust Domain Adaptive Object Detection With Unified Multi-Granularity Alignment},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {9161--9178},
  doi = {10.1109/tpami.2024.3416098}
}
Kostenlos starten →