EUVIMEDEUVIMED entdecken
Crossref

Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection

Xiaonan Lu, Wenhui Diao, Yongqiang Mao, Junxi Li, Peijin Wang, Xian Sun, Kun Fu

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (2) · 1844-1852

DOI: 10.1609/aaai.v37i2.25274 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Xiaonan Lu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 81-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-shot object detection, expecting detectors to detect novel classes with a few instances, has made conspicuous progress. However, the prototypes extracted by existing meta-learning based methods still suffer from insufficient representative information and lack awareness of query images, which cannot be adaptively tailored to different query images. Firstly, only the support images are involved for extracting prototypes, resulting in scarce perceptual information of query images. Secondly, all pixels of all support images are treated equally when aggregating features into prototype vectors, thus the salient objects are overwhelmed by the cluttered background. In this paper, we propose an Information-Coupled Prototype Elaboration (ICPE) method to generate specific and representative prototypes for each query image. Concretely, a conditional information coupling module is introduced to couple information from the query branch to the support branch, strengthening the query-perceptual information in support features. Besides, we design a prototype dynamic aggregation module that dynamically adjusts intra-image and inter-image aggregation weights to highlight the salient information useful for detecting query images. Experimental results on both Pascal VOC and MS COCO demonstrate that our method achieves state-of-the-art performance in almost all settings. Code will be available at: https://github.com/lxn96/ICPE.

Zitieren

APA

Lu, X., Diao, W., Mao, Y., Li, J., Wang, P., Sun, X., & Fu, K. (2023). Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2), 1844-1852. https://doi.org/10.1609/aaai.v37i2.25274

Vancouver

Lu X, Diao W, Mao Y, Li J, Wang P, Sun X, et al. Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(2):1844-1852. doi:10.1609/aaai.v37i2.25274

BibTeX
@article{Lu2023,
  author = {Lu, Xiaonan and Diao, Wenhui and Mao, Yongqiang and Li, Junxi and Wang, Peijin and Sun, Xian and Fu, Kun},
  title = {Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {2},
  pages = {1844--1852},
  doi = {10.1609/aaai.v37i2.25274}
}
Kostenlos starten →