EUVIMEDEUVIMED entdecken
Crossref

Save the Tiny, Save the All: Hierarchical Activation Network for Tiny Object Detection

Guangqian Guo, Pengfei Chen, Xuehui Yu, Zhenjun Han, Qixiang Ye, Shan Gao

IEEE Transactions on Circuits and Systems for Video Technology · 2024-01 · 34 (1) · 221-234

DOI: 10.1109/tcsvt.2023.3284161 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-01. Verfasst von Guangqian Guo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 95-mal zitiert (Crossref) und nennt 46 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tiny object detection (TOD) remains a challenging problem due to the extremely small size and weak feature presentations of tiny objects. Many effective methods have improved the detection of small objects below $32\times 32$ pixels to some extent, but the performance is still poor for the tiny objects below $16\times 16$ pixels. In this paper, we find that the aliasing between the features and object scales, namely feature-scale-aliasing, leads to the misalignment between feature subspaces and detection subspaces, and thus results in the interference of features, especially for tiny objects. To alleviate this, we propose a Hierarchical Activation (HA) method to obtain scale-specific feature subspaces by activating object features at different scales hierarchically. To this end, we design a Scale-Guided Feature Activation (SGFA) to decompose the original object-aliasing feature spaces into a group of scale-specific feature subspaces by scale-guided activation maps. Then, Scale-Specific Feature re-Coupling (SSFC) is used to enhance the feature subspaces by adaptively aggregating the feature subspaces from different groups. In addition, we propose to complement the scale-specific detailed information by a designed Detailed Information Compensation (DIC) method. Implementing HA, a multi-scale keypoint-based detector is constructed to improve the tiny object detection, referred to as Hierarchical Activation Network (HANet). Extensive experiments are carried out on three tiny object detection datasets, e.g., TinyPerson, AI-TOD, and TinyCOCO. Our HANet achieves 58.45% $AP_{50}^{all}$ , 22.1% $AP$ , and 15.76% $AP$ on TinyPerson, AI-TOD, and TinyCOCO, respectively, showing a significant performance gain over the competitors.

Zitieren

APA

Guo, G., Chen, P., Yu, X., Han, Z., Ye, Q., & Gao, S. (2024). Save the Tiny, Save the All: Hierarchical Activation Network for Tiny Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 34(1), 221-234. https://doi.org/10.1109/tcsvt.2023.3284161

Vancouver

Guo G, Chen P, Yu X, Han Z, Ye Q, Gao S. Save the Tiny, Save the All: Hierarchical Activation Network for Tiny Object Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(1):221-234. doi:10.1109/tcsvt.2023.3284161

BibTeX
@article{Guo2024,
  author = {Guo, Guangqian and Chen, Pengfei and Yu, Xuehui and Han, Zhenjun and Ye, Qixiang and Gao, Shan},
  title = {Save the Tiny, Save the All: Hierarchical Activation Network for Tiny Object Detection},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2024},
  volume = {34},
  number = {1},
  pages = {221--234},
  doi = {10.1109/tcsvt.2023.3284161}
}
Kostenlos starten →